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

    Neuronpedia

    INDEX
    Explanations

    numeric identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    1.16
     in
    1.06
    도
    1.04
    2
    1.03
    ও
    0.89
    も
    0.83
    for
    0.82
     for
    0.78
    もら
    0.75
     در
    0.71
    POSITIVE LOGITS
    0.82
    ны
    0.61
     on
    0.59
     It
    0.57
    녠
    0.57
     is
    0.54
    k
    0.54
    かけ
    0.53
     to
    0.52
    บน
    0.52
    Act Density 1.226%

    No Known Activations