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

    Neuronpedia

    INDEX
    Explanations

    sometimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뉸
    0.42
    を中心
    0.42
    欳
    0.41
     président
    0.41
     choisir
    0.40
     sobretudo
    0.39
     wszystkie
    0.38
     ricco
    0.37
    ろしく
    0.37
     tất
    0.37
    POSITIVE LOGITS
     sometimes
    0.73
     иногда
    0.69
    某些
    0.66
     Sometimes
    0.61
    Sometimes
    0.61
     parfois
    0.60
    sometimes
    0.60
     kadang
    0.60
    有时
    0.59
     Иногда
    0.58
    Act Density 0.127%

    No Known Activations