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

    Neuronpedia

    INDEX
    Explanations

    contracts and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.65
     نے
    0.62
    的
    0.61
     cáo
    0.59
     لیکن
    0.56
    ется
    0.55
    اکي
    0.55
    ра
    0.55
     са
    0.55
     زي
    0.55
    POSITIVE LOGITS
    and
    0.78
    int
    0.74
    ra
    0.70
    s
    0.67
     A
    0.66
     for
    0.66
    sh
    0.66
    for
    0.64
     S
    0.63
    ll
    0.63
    Act Density 0.020%

    No Known Activations