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

    Neuronpedia

    INDEX
    Explanations

    all rights reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     donn
    0.80
    ۰
    0.79
    ят
    0.76
    ْم
    0.76
     legitim
    0.75
    درا
    0.73
    有助于
    0.73
    0
    0.73
    在
    0.73
     ود
    0.71
    POSITIVE LOGITS
    v
    0.90
    f
    0.89
    い
    0.84
    тся
    0.83
    ま
    0.83
    트
    0.77
     большой
    0.75
    ều
    0.73
    ção
    0.71
     japan
    0.71
    Act Density 0.000%

    No Known Activations