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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries about improvement or understanding

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

    how to ask questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astify
    -0.59
     HasFactory
    -0.52
    ulipas
    -0.52
    AntiForgeryToken
    -0.51
    colgroup
    -0.50
    bootstrapcdn
    -0.49
    ########.
    -0.46
    yntaxException
    -0.46
    ptid
    -0.46
    SPJ
    -0.45
    POSITIVE LOGITS
    如何
    1.49
     如何
    1.29
     cómo
    1.21
    如何在
    1.19
    怎样
    1.19
    Cómo
    1.16
    How
    1.12
     how
    1.08
    怎樣
    1.08
    how
    1.07
    Act Density 0.004%

    No Known Activations