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

    Neuronpedia

    INDEX
    Explanations

    free of charge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     механи
    0.72
     رب
    0.64
     Đây
    0.64
    केन
    0.63
     поверхность
    0.63
    堭
    0.62
    RawO
    0.62
    द्योगिक
    0.62
    iejęt
    0.61
     Acá
    0.61
    POSITIVE LOGITS
    less
    1.81
    free
    1.77
     free
    1.73
    Free
    1.62
    lessness
    1.59
    lessly
    1.59
     Free
    1.56
     FREE
    1.48
    FREE
    1.47
    eless
    1.39
    Act Density 0.165%

    No Known Activations