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

    Neuronpedia

    INDEX
    Explanations

    mixed language numerals and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.70
    лке
    1.62
    iq
    1.57
    یان
    1.57
    ין
    1.56
    ię
    1.55
    iene
    1.54
    ições
    1.54
    ição
    1.50
    يو
    1.45
    POSITIVE LOGITS
    いた
    1.67
    서
    1.63
    ৬
    1.54
    นี้
    1.53
    이면
    1.52
    २
    1.49
    した
    1.48
    ছেন
    1.45
    $
    1.43
    %
    1.33
    Act Density 0.360%

    No Known Activations