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

    Neuronpedia

    INDEX
    Explanations

    people, individuals, person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    리
    0.60
    ار
    0.58
    ar
    0.58
    P
    0.58
    م
    0.58
    י
    0.58
    ي
    0.56
    Io
    0.52
    SEN
    0.52
    uatan
    0.52
    POSITIVE LOGITS
    了一个
    0.47
    いる
    0.46
    crs
    0.44
    ки
    0.44
    多い
    0.43
    咣
    0.43
    重要的是
    0.40
    人的
    0.40
    ники
    0.40
     Jans
    0.40
    Act Density 0.353%

    No Known Activations