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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _die
    -0.07
    .'/
    -0.07
    .writeObject
    -0.07
    ास
    -0.06
    Trong
    -0.06
     dei
    -0.06
     قاب
    -0.06
    _bed
    -0.06
    不要
    -0.06
     refreshed
    -0.06
    POSITIVE LOGITS
    .EndsWith
    0.07
    _CHAR
    0.07
    preneur
    0.06
     actionBar
    0.06
     treffen
    0.06
    LogLevel
    0.06
     подход
    0.05
    oser
    0.05
    itect
    0.05
     düşün
    0.05
    Act Density 0.011%

    No Known Activations