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

    Neuronpedia

    INDEX
    Explanations

    optical aberrations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نا
    0.91
    ’
    0.88
    AN
    0.84
     transforma
    0.80
    That
    0.78
    OR
    0.77
     लेकर
    0.76
    à
    0.76
    ח
    0.73
    out
    0.73
    POSITIVE LOGITS
    :
    0.92
    تها
    0.87
    stantial
    0.87
    weiter
    0.87
    season
    0.86
    feeling
    0.85
    تك
    0.84
    تری
    0.84
    لة
    0.82
    toare
    0.82
    Act Density 0.000%

    No Known Activations