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

    Neuronpedia

    INDEX
    Explanations

    international regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuant
    0.45
     encapsulation
    0.43
     envelopp
    0.41
     envis
    0.40
     eradic
    0.39
     pobreza
    0.39
    ంటి
    0.39
    ловой
    0.38
     SafeArea
    0.38
    你去
    0.38
    POSITIVE LOGITS
    Shore
    0.46
    Mary
    0.46
    犇
    0.41
     அதிச
    0.40
    chny
    0.39
     फिल्में
    0.38
     अलग
    0.38
     kı
    0.38
    parallel
    0.38
    眞
    0.38
    Act Density 0.065%

    No Known Activations