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

    Neuronpedia

    INDEX
    Explanations

    referred

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trim
    -0.07
     Вал
    -0.07
     Caller
    -0.06
     Raq
    -0.06
     But
    -0.06
     अख
    -0.06
    _norm
    -0.06
    intree
    -0.06
    cision
    -0.06
     zvol
    -0.06
    POSITIVE LOGITS
    ุร
    0.07
     ظ
    0.06
     sow
    0.06
    خوان
    0.06
    0.06
    ONENT
    0.06
    _Server
    0.06
    otype
    0.06
     gusto
    0.06
    assistant
    0.06
    Act Density 0.008%

    No Known Activations