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

    Neuronpedia

    INDEX
    Explanations

    fossilized or fossilization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    0.64
    un
    0.59
    textured
    0.59
    ill
    0.57
    the
    0.57
    taining
    0.56
    ,
    0.56
    ul
    0.56
    g
    0.54
    za
    0.53
    POSITIVE LOGITS
     الأ
    0.71
    م
    0.66
     الأطفال
    0.66
    К
    0.62
     哈
    0.60
     eserc
    0.59
     uygulama
    0.59
     Einf
    0.58
     dumbbells
    0.58
    蒨
    0.58
    Act Density 0.001%

    No Known Activations