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

    Neuronpedia

    INDEX
    Explanations

    License

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of license‐header markers—i.e. it spotlights the word “License” (and related license‐block tags) in source comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    εκ
    -0.07
     controvers
    -0.06
    .processor
    -0.06
    stores
    -0.06
    throp
    -0.06
    ARGE
    -0.06
     jente
    -0.06
     context
    -0.06
     بیشتر
    -0.06
     //-
    -0.06
    POSITIVE LOGITS
    /sdk
    0.08
     https
    0.07
     cuff
    0.07
    _vm
    0.06
     Closing
    0.06
     Professional
    0.06
     doomed
    0.06
    ）。↵
    0.06
     targetType
    0.06
     OUT
    0.06
    Act Density 0.001%

    No Known Activations