We hypothesize that polysemantic neurons may be resolvable by unfolding networks or training to avoid polysemanticity.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Polysemantic neurons are a major challenge for the circuits agenda, because N meanings in one neuron times M in another creates NxM effective connections that cannot be considered individually.claim0.829
  Precise characterization of why polysemanticity poses a combinatorial obstacle to circuit analysis
• No established method for resolving polysemantic neurons into pure features at scalequestion0.827
  Identified gap linking polysemanticity challenge to disentangled representations literature
• Training models with sparse activations cannot fully prevent polysemanticity because cross-entropy loss creates incentives for polysemantic neurons even without superpositionclaim0.807
  Author's conclusion after extensive investigation of architectural approaches to monosemanticity
• Polysemantic Neuronconcept0.793
  A neuron that responds to multiple unrelated inputs, posing a major challenge for circuit-level interpretation
• Models with 1-hot activation sparsity still have polysemantic neurons; single neuron trained on 4 mutually exclusive features prefers polysemantic representation with loss ~0.7 vs 0.8finding0.786
  Counter-example disproving that architectural sparsity alone can prevent polysemanticity
• Superposition is in some sense deliberate: the model converts pure neurons into polysemantic neurons to store more features in fewer neurons.claim0.780
  Interpretation of the cars-in-superposition circuit finding as an intentional representational strategy
• Learning neural networks can enable 'chunking' and rescale problem-solving to higher organizational levels, a mechanism intrinsic to transitions in individuality.hypothesis0.761
• The remarkable ability of neurons to unify toward a centralized self is an evolutionary pivot of far earlier cell communication strategies that first solved problems in navigating anatomical morphospace.hypothesis0.760
  Proposes an evolutionary trajectory linking morphogenesis to neural cognition.