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

    Neuronpedia

    INDEX
    Explanations

    find more information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     upang
    0.46
    ഴി
    0.45
     Enables
    0.41
     بہانہ
    0.41
     फिज
    0.40
     celui
    0.40
    ндагы
    0.38
     pitanje
    0.38
     deoarece
    0.38
     puisqu
    0.38
    POSITIVE LOGITS
     more
    0.79
     más
    0.64
    更多
    0.60
     더
    0.56
    more
    0.56
     более
    0.54
     περισσότε
    0.53
     più
    0.51
     أكثر
    0.51
    Más
    0.51
    Act Density 0.005%

    No Known Activations