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

    Neuronpedia

    INDEX
    Explanations

    digits 1 and 19

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Qo
    0.75
    ๘
    0.75
    丏
    0.74
    midrule
    0.72
    ๖
    0.70
    ⣤
    0.70
    嬛
    0.69
    တစ်ခု
    0.68
     سکتی
    0.68
    ElementException
    0.67
    POSITIVE LOGITS
    1
    2.38
     ۱۹
    2.22
    ۱۹
    1.89
     ١
    1.82
    ১৯
    1.81
    १९
    1.78
     १९
    1.72
    １
    1.68
     ၁
    1.66
     ១
    1.56
    Act Density 0.097%

    No Known Activations