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

    Neuronpedia

    INDEX
    Explanations

    iterating lines in files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     darling
    0.39
     ধরার
    0.37
     dame
    0.37
     фрон
    0.37
    ','%
    0.37
     nincs
    0.37
     монасты
    0.36
     polls
    0.35
    кана
    0.35
    有的
    0.34
    POSITIVE LOGITS
    overy
    0.42
     immer
    0.41
    ורך
    0.38
    urno
    0.38
     sempre
    0.35
    ন
    0.35
    uso
    0.34
     interpretación
    0.34
     Drawn
    0.34
    నూ
    0.34
    Act Density 0.002%

    No Known Activations