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

    Neuronpedia

    INDEX
    Explanations

    variable names in loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kalau
    0.45
    мери
    0.43
    introduction
    0.42
     дуже
    0.42
     Приступ
    0.42
     mauvaise
    0.41
    lar
    0.40
    ми
    0.40
    лишком
    0.40
    ສຸດ
    0.39
    POSITIVE LOGITS
    喺
    0.51
     sake
    0.48
     belonging
    0.47
     iterate
    0.46
     member
    0.45
     each
    0.43
    ([
    0.40
     participating
    0.40
    iterrows
    0.40
     iteratively
    0.39
    Act Density 0.037%

    No Known Activations