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

    Neuronpedia

    INDEX
    Explanations

    file size limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    barth
    -0.08
    уля
    -0.08
    _Impl
    -0.07
    .pad
    -0.07
    രണം
    -0.07
    天气
    -0.07
     comprom
    -0.07
    izabeth
    -0.07
     literally
    -0.07
    .padding
    -0.07
    POSITIVE LOGITS
    限制
    0.11
     restricciones
    0.10
     제한
    0.09
     ограничения
    0.09
     Ог
    0.09
     stipulated
    0.09
     limit
    0.09
     रकम
    0.09
    Restr
    0.09
     सीमा
    0.09
    Act Density 0.003%

    No Known Activations