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

    Neuronpedia

    INDEX
    Explanations

    multiple times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    倍
    1.01
     倍
    0.83
     TIMES
    0.78
     மடங்கு
    0.73
     fold
    0.72
     times
    0.69
     gấp
    0.69
     folds
    0.67
    fold
    0.66
     गुना
    0.63
    POSITIVE LOGITS
     Many
    0.42
    无数
    0.40
     countless
    0.40
     nhiều
    0.39
     Two
    0.39
     nombreuses
    0.38
     正
    0.38
     inú
    0.38
    结
    0.38
     Nhiều
    0.37
    Act Density 0.007%

    No Known Activations