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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     üzeri
    0.38
    態
    0.38
    vrir
    0.37
    Miche
    0.37
    自身的
    0.37
     consistently
    0.37
    ID
    0.35
     requiring
    0.35
    onial
    0.35
    وريا
    0.35
    POSITIVE LOGITS
    ല്ലാ
    0.46
     भग्न
    0.42
    ить
    0.39
     Дж
    0.39
    наче
    0.39
     흥
    0.39
    다가
    0.38
     trzec
    0.38
     சிகிச்ச
    0.37
     फांसी
    0.37
    Act Density 0.001%

    No Known Activations