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

    Neuronpedia

    INDEX
    Explanations

    men vs women

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Giải
    1.38
    ה
    1.16
    К
    1.13
    То
    1.09
    迤
    1.08
    ﻜ
    1.07
    اس
    1.05
    上海
    1.03
     Tập
    1.03
     Câu
    1.02
    POSITIVE LOGITS
    ojen
    1.39
    nce
    1.17
    ry
    1.13
    imiz
    1.11
    ans
    1.10
    ből
    1.10
    imizde
    1.07
    lö
    1.07
    able
    1.05
    ryt
    1.04
    Act Density 0.011%

    No Known Activations