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

    Neuronpedia

    INDEX
    Explanations

    expressing negative quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    浣
    0.79
    拉
    0.78
    е
    0.77
    在
    0.73
    та
    0.73
    來
    0.71
    مر
    0.69
    特
    0.69
    會
    0.67
    秋冬
    0.67
    POSITIVE LOGITS
    </h2>
    0.79
    ",
    0.78
     ciri
    0.77
     are
    0.70
    ש
    0.68
    지만
    0.68
    "،
    0.67
    <0x0D>
    0.66
    য়
    0.66
     vaso
    0.64
    Act Density 0.001%

    No Known Activations