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

    Neuronpedia

    INDEX
    Explanations

    foreign language verb endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.05
    i
    0.91
    ie
    0.89
    ној
    0.86
    for
    0.83
    b
    0.82
    c
    0.81
    <0x80>
    0.80
     bằng
    0.80
     дан
    0.79
    POSITIVE LOGITS
    લ
    1.21
    ل
    1.13
    ：
    1.10
    વ
    1.02
    It
    1.02
    ने
    1.00
    ट
    0.97
    В
    0.97
    、
    0.91
    וי
    0.90
    Act Density 0.017%

    No Known Activations