Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash

    legal terminology and references to court proceedings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to layout metadata—particularly floating‐point numbers used for indent or positioning (e.g. “0.62890625,” “1.6025390625,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Paint
    -0.07
     tokens
    -0.07
     ADHD
    -0.07
     Fatal
    -0.07
     NST
    -0.06
    usty
    -0.06
     Qualität
    -0.06
    Planning
    -0.06
     Shot
    -0.06
     от
    -0.06
    POSITIVE LOGITS
    Courtesy
    0.07
    	namespace
    0.07
    earned
    0.06
     поможет
    0.06
     RTE
    0.06
     
    0.06
     tapi
    0.06
     finanzi
    0.06
    -tech
    0.06
    imming
    0.06
    Act Density 0.004%

    No Known Activations