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

    Neuronpedia

    INDEX
    Explanations

    programming variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     අපි
    0.61
    Chúng
    0.59
    我们
    0.59
     incisions
    0.57
     chúng
    0.57
    etzungen
    0.56
     我们
    0.55
     you
    0.55
     we
    0.55
    waż
    0.55
    POSITIVE LOGITS
    m
    0.88
    ’
    0.84
    as
    0.80
    and
    0.78
    é
    0.75
    変数
    0.73
    т
    0.70
    g
    0.69
    ก
    0.68
    त
    0.68
    Act Density 0.391%

    No Known Activations