SUMMARYResearchers found evidence that Anthropic’s Claude has formed a small set of internal neural patterns that play a special role compared with its other processing. The work draws an analogy to conscious access in human brains, suggesting these patterns help the model support deliberate reasoning and can be identified in its internal activity.
As you read this sentence, circuits in your brain are adjusting your posture, controlling your breathing, and transforming lines and curves on the screen into recognizable words. Most of this processing is invisible to you. But some of what takes place in your brain you do have access to—an image that pops into your head, or a deliberate plan you make about where to go shopping. Neuroscientists and philosophers sometimes refer to the latter type of brain activity as “consciously accessible,” to distinguish it from all the other processing that goes on unconsciously. This activity has special properties: we can describe it, control it, and use it for deliberate reasoning, in contrast to all the automatic processing that goes on without our awareness.
In a new paper, we present evidence that a similar distinction has emerged in modern language models like Claude. We find that Claude has developed a small collection of internal neural patterns that, compared to all its other internal processing, play a special role.
Full paper: http://transformer-circuits.pub/2026/workspace/index.html
Demo: http://neuronpedia.org/jlens
X post: https://x.com/AnthropicAI/status/2074185348142280912