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

    Neuronpedia

    INDEX
    Explanations

    100 times, labor, Mbps, rainy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مس
    0.38
    the
    0.37
     únic
    0.36
    مش
    0.35
    ’,
    0.34
    مانی
    0.33
    keb
    0.33
    б
    0.33
    Baca
    0.33
    ?)
    0.32
    POSITIVE LOGITS
    า
    0.46
    ing
    0.41
    ਾ
    0.41
    ot
    0.36
    ü
    0.34
    器件
    0.33
    ia
    0.33
    ingin
    0.33
    okra
    0.30
    他对
    0.30
    Act Density 0.345%

    No Known Activations