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

    Neuronpedia

    INDEX
    Explanations

    comma int in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iteratively
    0.32
    inds
    0.31
    прави
    0.31
    assam
    0.31
     aru
    0.31
     foli
    0.30
    ycop
    0.30
     Normandie
    0.30
    ทุก
    0.30
    riminate
    0.30
    POSITIVE LOGITS
    లలో
    0.32
    widgetTo
    0.32
    ራስ
    0.31
     형식
    0.31
    ებში
    0.30
     ADMINISTR
    0.29
     শুরুর
    0.29
    ﺕ
    0.29
    ത്തിയത്
    0.28
    中的
    0.28
    Act Density 0.002%

    No Known Activations