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

    Neuronpedia

    INDEX
    Explanations

    problem / elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ĝi
    0.44
    он
    0.42
    تيجة
    0.41
    It
    0.40
    这是
    0.40
    ރ
    0.40
     цена
    0.39
    ק
    0.39
    佢
    0.38
    Это
    0.38
    POSITIVE LOGITS
     your
    0.47
     niektórych
    0.42
     aboard
    0.42
    ään
    0.42
    ziemy
    0.41
     diferenciar
    0.41
     forskj
    0.41
     manly
    0.40
     আর
    0.40
     여러분
    0.40
    Act Density 0.037%

    No Known Activations