Spallation Neutron Source (SNS) Accelerators

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

• "What do African rhythms, spallation neutron source (SNS) accelerators in nuclear physics, string theory (stringology) in computer science, and an ancient algorithm described by Euclid have in common? The short answer is: patterns distributed as evenly as possible."concept0.773
  Opening rhetorical question that encapsulates the paper's central claim: multiple domains share the principle of even distribution.
• Polysemantic Neuronconcept0.685
  A neuron that responds to multiple unrelated inputs, posing a major challenge for circuit-level interpretation
• NLAs bridge unsupervised concept-discovery methods (e.g., SAEs) and supervised activation-verbalization methods (e.g., activation oracles)claim0.668
  The paper positions NLAs as combining unsupervised learning with direct readability.
• AUS_N is a weaker correlate of θ50 than S_max across E3 backbonesfinding0.664
  E3 finding distinguishing the two geometry summaries; breadth less predictive than peak height
• Double standard in sentience attribution across substratesclaim0.662
  Rouleau & Levin argue: behavioral patterns attributed to sentience in animals should be afforded same interpretation in plants and other systems without neural substrate bias.
• 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 0.8finding0.658
  Counter-example disproving that architectural sparsity alone can prevent polysemanticity
• Caltech SPARinstitute0.654
  Research group affiliated with both authors; part of institutional affiliation for this work.
• Eight Sentience Criteria (Crump et al.)framework0.654
  Quantitative, flexible framework for assessing sentience: nociception, sensory integration, analgesia, trade-offs, self-protection, learning, preference.