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

    Neuronpedia

    INDEX
    Explanations

    Horizontal separators

    np_max-act · gemini-2.0-flash

    the start of an assistant reply / assistant-role or reply-boundary markers in the conversation.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    调
    -0.07
     hours
    -0.07
     Quarry
    -0.06
     <->
    -0.06
    885
    -0.06
     Rob
    -0.06
    �
    -0.06
    Kyle
    -0.06
    리에
    -0.06
     responseBody
    -0.06
    POSITIVE LOGITS
    @param
    0.07
    >".$
    0.07
    کاران
    0.07
     المس
    0.07
    .dateTimePicker
    0.07
     ll
    0.06
    button
    0.06
    .Positive
    0.06
     pentru
    0.06
     největší
    0.06
    Act Density 0.042%

    No Known Activations