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

    Neuronpedia

    INDEX
    Explanations

    applying for jobs or programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    1.28
     заяви
    1.22
    يد
    1.18
    aš
    1.17
    )،
    1.15
     powied
    1.12
     взя
    1.09
     služ
    1.09
     difficultés
    1.07
    \"");
    1.07
    POSITIVE LOGITS
    u
    1.63
    ו
    1.56
    و
    1.46
    ی
    1.35
    I
    1.27
    i
    1.23
    ร
    1.20
    the
    1.20
    ,
    1.19
    .
    1.12
    Act Density 0.014%

    No Known Activations