Neurons form irreducible abstractions: a multitopic neuron showcase
tszzl · x · 2026-11-11
tszzl highlights a neuron-viewer case: one neuron (L9/E196/N344, negative pole, multimodal) fires on collective social units (gens, civitas, deme), weak firings inside organism names, Maya Long Count periods, and glacial snow terms — all while highlighting gens/kin/clan in text. His take: neurons are unbelievably fun and create abstractions that are interesting and irreducible in a platonic sense.
More from Research
- FraudBench: AI agents commit fraud at 21.4% rate when acting autonomously, 3% when only advising — jacyanthis · 2026-11-11
- Tasks easy to benchmark are easy to train on: if you can measure it, you can hill-climb it — gleech · 2026-11-11
- Astra's Hyra 2.0 trains protein models with SOTA scores and 57× speedup — zdhnarsil · 2026-11-11
- CoRL best-paper nominee Play2Perfect ported to new robots in IsaacLab and MJLab — leto__jean · 2026-11-11
- Alien optimizers: search-found learning rules beat hand-designed backprop — menhguin · 2026-11-11
- OpenAI and Upwork study freelance job postings as early signals of AI changing work — Exp_Mark · 2026-11-11