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

    Neuronpedia

    INDEX
    Explanations

    announcements of public actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.66
    一
    0.60
    of
    0.52
    會
    0.51
    L
    0.50
     at
    0.50
    AL
    0.50
    G
    0.48
     to
    0.47
     be
    0.47
    POSITIVE LOGITS
     случаи
    0.64
     эффект
    0.57
     actualizaciones
    0.57
     зависи
    0.56
     проверки
    0.56
     فريبي
    0.56
    ли
    0.56
     rupani
    0.56
    та
    0.55
     diarias
    0.55
    Act Density 0.523%

    No Known Activations