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

    Neuronpedia

    INDEX
    Explanations

    gems and clear substances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이었
    0.76
    ды
    0.70
    ві
    0.69
    할
    0.68
    تی
    0.66
    ş
    0.65
    이었다
    0.64
    жи
    0.64
    ш
    0.64
     đợi
    0.62
    POSITIVE LOGITS
    ↵
    0.97
    il
    0.66
    ON
    0.64
     U
    0.64
    et
    0.63
     I
    0.63
    LER
    0.61
    em
    0.61
    TES
    0.59
    Danh
    0.59
    Act Density 0.258%

    No Known Activations