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

    Neuronpedia

    INDEX
    Explanations

    list and loop structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    1.29
    يات
    1.20
    ן
    1.20
    larda
    1.15
    larınız
    1.13
    ra
    1.13
    রা
    1.09
    stes
    1.09
    ları
    1.08
    lijk
    1.08
    POSITIVE LOGITS
    Το
    1.34
    $\
    1.20
    Как
    1.20
    ۸
    1.18
    ία
    1.16
    Ν
    1.14
    Một
    1.13
    와
    1.09
    ﻥ
    1.09
    Η
    1.08
    Act Density 0.255%

    No Known Activations