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
     Rohingya
    -0.07
     доступ
    -0.06
     محدود
    -0.06
     CROSS
    -0.06
    ments
    -0.06
     Bout
    -0.06
     Clamp
    -0.06
     informations
    -0.06
    約
    -0.06
     colabor
    -0.06
    POSITIVE LOGITS
     horm
    0.06
    _PRICE
    0.06
    .navigate
    0.06
    Method
    0.06
     therm
    0.06
     trousers
    0.06
    tabla
    0.06
     -=
    0.06
    -tabs
    0.06
     Thermal
    0.06
    Act Density 0.000%

    No Known Activations