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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (padding
    -0.07
    .stack
    -0.06
     مجموعة
    -0.06
     Empresa
    -0.06
    cessive
    -0.06
    .CheckBox
    -0.06
    -0.06
    periments
    -0.06
     手
    -0.06
    .getStatusCode
    -0.06
    POSITIVE LOGITS
    _AdjustorThunk
    0.07
     Kup
    0.07
    .ApplyResources
    0.07
     revered
    0.06
    .')
    0.06
    QM
    0.06
    。」
    0.06
     serializer
    0.06
    šní
    0.06
     especific
    0.06
    Act Density 0.002%

    No Known Activations