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

    Neuronpedia

    INDEX
    Explanations

    how can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.52
    of
    0.46
    均衡
    0.43
    த்திர
    0.43
    으면
    0.42
     overwhelmingly
    0.41
    意味
    0.40
    意
    0.40
     compet
    0.39
     participating
    0.39
    POSITIVE LOGITS
     структуры
    0.57
     કેટલાક
    0.55
     نیاز
    0.54
    leicht
    0.52
     estructura
    0.51
     لینک
    0.50
    ម
    0.50
     божомолдор
    0.49
     ג
    0.48
    utérus
    0.48
    Act Density 0.000%

    No Known Activations