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

    Neuronpedia

    INDEX
    Explanations

    acknowledging limitations, facts, or feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    1.12
    al
    1.09
    स
    1.03
    ar
    1.01
    s
    0.92
    as
    0.91
     for
    0.89
    4
    0.83
    7
    0.82
    for
    0.79
    POSITIVE LOGITS
    '
    1.13
    し
    0.92
     is
    0.90
    ように
    0.89
     सामने
    0.84
    沒有
    0.79
    精密
    0.79
    符合
    0.78
     बेहतर
    0.75
    牛肉
    0.75
    Act Density 0.009%

    No Known Activations