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

    Neuronpedia

    INDEX
    Explanations

    springframework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    1.10
    它
    1.07
    и
    0.96
    ı
    0.96
    我们
    0.95
    我
    0.94
     of
    0.91
    ера
    0.89
    文件
    0.86
    ла
    0.85
    POSITIVE LOGITS
    springframework
    1.19
    ↵
    1.09
    ک
    1.04
    ad
    1.00
    y
    0.95
    ’
    0.94
    st
    0.94
    ก
    0.92
    r
    0.89
    ק
    0.86
    Act Density 0.001%

    No Known Activations