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

    Neuronpedia

    INDEX
    Explanations

    specific choices or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    และ
    0.86
     మరియు
    0.85
     וא
    0.80
     Và
    0.79
     Sa
    0.77
    이자
    0.77
    和小
    0.76
     và
    0.75
     כאשר
    0.75
     và
    0.74
    POSITIVE LOGITS
     مثلا
    1.16
    उदाहरण
    0.98
     variously
    0.97
    either
    0.97
    might
    0.95
     might
    0.94
    যেমন
    0.94
     например
    0.93
    उदा
    0.93
    某种
    0.92
    Act Density 0.196%

    No Known Activations