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

    Neuronpedia

    INDEX
    Explanations

    adverbs of manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    続ける
    0.39
     स्टेप
    0.38
    厳
    0.37
     LOCCTR
    0.35
     discomfort
    0.34
     엄
    0.33
     ನೋಡ
    0.33
     ಬಳಸ
    0.33
     unavoid
    0.33
    用到
    0.32
    POSITIVE LOGITS
     easily
    0.71
     cleanly
    0.66
     readily
    0.64
    easily
    0.63
     successfully
    0.62
     nicely
    0.61
     легко
    0.57
     succesfully
    0.56
     beautifully
    0.55
     smoothly
    0.55
    Act Density 0.042%

    No Known Activations