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

    Neuronpedia

    INDEX
    Explanations

    topic titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aldı
    1.20
     funcion
    1.10
    他
    1.09
     invoc
    1.08
     compartilh
    1.06
    də
    1.06
     multiplicar
    1.06
     desenvolv
    1.05
     accion
    1.05
     avaliar
    1.05
    POSITIVE LOGITS
    س
    1.45
    .
    1.35
    ons
    1.22
     was
    1.15
    ీ
    1.14
    то
    1.12
    ح
    1.11
    ج
    1.10
    ри
    1.05
    с
    1.05
    Act Density 0.044%

    No Known Activations