ResearchNov 18, 2026 · 00:371 source
Goodfire Identifies "Neuron Communities" for Arithmetic and Date Recall in LLMs
From marketbrief.now
Goodfire has identified "Neuron Communities," small groups of neurons that collaborate to perform specific tasks inside large language models. The research startup found that these small clusters are responsible for common behaviors such as arithmetic, recalling dates, or producing text in all capital letters.
The finding comes amid an ongoing dispute with researchers at OpenAI, Google DeepMind, and Anthropic over how legible AI neurons actually are. Critics have challenged Goodfire's previous claim that neural networks are functionally sparse, arguing that a 2.9% increase in model loss—which Goodfire called modest after ablating 92.2% of the weakest neuron activations in Alibaba's 35B parameter Qwen3.6 model—would actually represent a massive loss in training compute.
Sources
Content history (2)
- 2026-11-17 · Summary · vi · Replaced stored textGoodfire đã xác định được các "neuron communities" giúp LLMs có khả năng ghi nhớ các phép…Goodfire đã xác định được các "Neuron Communities", những nhóm Neuron nhỏ phối hợp với nh…
- 2026-11-17 · Title · vi · Replaced stored textGoodfire xác định các "neuron communities" giúp LLMs ghi nhớ phép tính và ngày thángGoodfire xác định các "Neuron Communities" giúp LLMs thực hiện phép tính và ghi nhớ ngày …
One ranked edition, every morning
The stories that matter today. Free, cancel anytime.
Telegram @aidr_today