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

    Neuronpedia

    INDEX
    Explanations

    not get rich quick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тря
    0.52
    MovieModal
    0.48
    Brow
    0.48
    приклад
    0.47
    癃
    0.46
    圧
    0.45
    Чтобы
    0.44
    閬
    0.44
    מצע
    0.43
    Puede
    0.43
    POSITIVE LOGITS
     buddhist
    0.48
    }
    0.48
     Muslims
    0.45
     Buddhists
    0.45
    ec
    0.43
    s
    0.43
    <0x80>
    0.43
     Buddhist
    0.41
    '
    0.41
    ł
    0.41
    Act Density 0.007%

    No Known Activations