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

    Neuronpedia

    INDEX
    Explanations

    final year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    0.79
    it
    0.71
    r
    0.67
    f
    0.66
    g
    0.63
    k
    0.60
    ing
    0.59
    on
    0.59
     and
    0.59
    t
    0.59
    POSITIVE LOGITS
    问题的
    0.38
    ני
    0.38
     Такие
    0.34
     Tö
    0.34
    UIT
    0.34
     등의
    0.34
    ᐈ
    0.34
    脘
    0.34
    ﮗ
    0.34
     సమస్య
    0.33
    Act Density 0.000%

    No Known Activations