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

    Neuronpedia

    INDEX
    Explanations

    how things would change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உள்ளார்
    0.48
    氢
    0.45
     crystall
    0.43
     гла
    0.41
    一次
    0.41
    事項
    0.40
     Empirical
    0.40
     Evaluations
    0.40
     высоким
    0.40
     новым
    0.39
    POSITIVE LOGITS
     minuman
    0.47
     čega
    0.47
     inklusive
    0.47
     belonging
    0.47
     perpetrated
    0.47
    chließlich
    0.46
     पैसे
    0.46
     probabilmente
    0.46
     damal
    0.45
     sebagai
    0.45
    Act Density 0.011%

    No Known Activations