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

    Neuronpedia

    INDEX
    Explanations

    command line utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elier
    0.46
     анали
    0.46
     ต่อ
    0.43
    чите
    0.43
    ummer
    0.43
    ทั้งหมด
    0.42
    ègues
    0.42
     rained
    0.42
     выяс
    0.42
     গুলির
    0.42
    POSITIVE LOGITS
    پا
    0.48
    پ
    0.46
    ణ్
    0.45
    製作
    0.43
     sanctions
    0.43
    ಾರೆ
    0.43
    擁有
    0.42
    ساز
    0.42
    Сан
    0.42
    کار
    0.42
    Act Density 0.000%

    No Known Activations