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

    Neuronpedia

    INDEX
    Explanations

    you followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !'
    0.52
     الت
    0.50
    णार्‍या
    0.49
    !"
    0.49
    มอง
    0.49
     penilaian
    0.49
     inhibition
    0.48
     در
    0.47
     ص
    0.47
     infringement
    0.47
    POSITIVE LOGITS
    ravariant
    0.47
    первых
    0.46
    不足
    0.46
    ů
    0.46
    OUSE
    0.42
    нинград
    0.42
    ieten
    0.42
     ਹੋ
    0.42
    ToTensor
    0.42
    糖
    0.42
    Act Density 0.000%

    No Known Activations