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

    Neuronpedia

    INDEX
    Explanations

    Non-English words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    လာ
    0.44
    勒
    0.41
     Gall
    0.40
     eases
    0.40
     Ajust
    0.39
     disparities
    0.39
     Ispol
    0.39
     Allo
    0.38
    猀
    0.38
    ب
    0.38
    POSITIVE LOGITS
    인데
    0.46
     истории
    0.43
    ăzi
    0.43
     कुमारी
    0.43
     هیچ
    0.42
     неизвест
    0.41
    歴史
    0.40
    য়নের
    0.40
    usehen
    0.39
    kc
    0.39
    Act Density 0.001%

    No Known Activations