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

    Neuronpedia

    INDEX
    Explanations

    Japanese names containing "ichi"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    If
    -3.00
     If
    -2.84
     These
    -2.73
    It
    -2.56
     They
    -2.53
    t
    -2.53
     Each
    -2.47
    They
    -2.45
    新型コロナ
    -2.28
    鬭
    -2.25
    POSITIVE LOGITS
    ть
    3.06
     fiables
    2.70
    ar
    2.67
    啬
    2.48
    喑
    2.44
     одного
    2.38
    すすめ
    2.38
    䊏
    2.28
    mente
    2.20
    zość
    2.20
    Act Density 0.004%

    No Known Activations