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

    Neuronpedia

    INDEX
    Explanations

    cost per

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    size
    0.79
    tai
    0.77
    lan
    0.76
     asos
    0.75
     tenham
    0.75
    सिले
    0.75
    sw
    0.74
     tenha
    0.74
    smith
    0.73
     Kleid
    0.73
    POSITIVE LOGITS
    .`);
    0.80
    Speaker
    0.71
    лії
    0.71
    োলার
    0.69
     jì
    0.68
    ობით
    0.65
     Fiverr
    0.65
    ‌ی
    0.64
    秘
    0.64
    ๏
    0.63
    Act Density 0.002%

    No Known Activations