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

    Neuronpedia

    INDEX
    Explanations

    words starting with re

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.05
    中医
    0.76
    大
    0.73
     is
    0.65
    位置
    0.64
     misdemean
    0.63
    水位
    0.63
     indenture
    0.62
     adjudication
    0.60
    ب
    0.60
    POSITIVE LOGITS
    ్‌
    0.74
    ،
    0.73
    دي
    0.67
    斯的
    0.67
    ция
    0.64
    oque
    0.61
    al
    0.61
    nach
    0.60
    밌
    0.59
    becca
    0.59
    Act Density 0.105%

    No Known Activations