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

    Neuronpedia

    INDEX
    Explanations

    foreign language elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulation
    0.46
    늄
    0.42
     $_{
    0.41
    ulação
    0.41
    ap
    0.40
    écution
    0.40
    atering
    0.40
    વાહી
    0.40
     Probate
    0.40
    ating
    0.40
    POSITIVE LOGITS
    ים
    0.55
    ς
    0.47
    s
    0.47
    ّ
    0.45
     cosidd
    0.43
    يي
    0.43
    კ
    0.42
    ը
    0.41
     fierce
    0.40
    โต
    0.40
    Act Density 0.103%

    No Known Activations