Sparse low-cardinality circuits implement competence; 0.2% of neurons handle shared computation across all cyclic tasks.

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

• A sparse set of 28 MLP neurons at layer 18 (~0.2% of MLP) are reused across all cyclic tasksfinding0.781
  Quantitative finding identifying the specific neurons responsible for generic addition
• Neural networks compute cyclic concepts in generic substrate machinery (base-10 addition) not naturally cyclic computation.claim0.781
• Approximately 0.2% of MLP neurons at layer 18 (~28 neurons) are sufficient to account for the generic addition computation across all cyclic tasksclaim0.776
  Claim about the sparsity and sufficiency of the identified neuron set
• Cells and cellular networks have problem-solving capacities that allow them to navigate entirely novel stressors (e.g., barium) without prior selection, implying a general competency beyond hardwired responses.claim0.770
  Derived from the planarian barium adaptation finding.
• Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models (Marks et al., 2025)concept0.762
  Cited as enabling precise behavioral control through SAE features, extending the same methodological line
• There is a many-to-many mapping between neurons and concepts, meaning multiple high-level causal variables might be encoded in overlapping groups of neuronsclaim0.757
  Fundamental theoretical claim motivating DAS, attributed to Smolensky/Rumelhart/McClelland.
• 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.claim0.756
  Precise characterization of why polysemanticity poses a combinatorial obstacle to circuit analysis
• All neuronal processing and action selection minimize variational free energy, unifying perception, action, and learning.claim0.752
  Fundamental assertion: single imperative (free energy minimization) explains diverse cognitive and neural phenomena.