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

    Neuronpedia

    INDEX
    Explanations

    smaller, fewer, less

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ものです
    0.43
    particular
    0.42
    setImageResource
    0.41
     منتقل
    0.39
    γη
    0.39
    datatype
    0.39
    送
    0.38
    datac
    0.38
     Hilde
    0.38
    ෲ
    0.38
    POSITIVE LOGITS
     smaller
    0.58
     мень
    0.50
    👊
    0.49
     workings
    0.47
     nhỏ
    0.47
     spaced
    0.47
     kleinere
    0.46
     rubbish
    0.45
     것에
    0.45
     amiss
    0.44
    Act Density 0.011%

    No Known Activations