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

    Neuronpedia

    INDEX
    Explanations

    feature matching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    코드
    0.66
     alebo
    0.66
    もら
    0.66
    em
    0.65
    ನ
    0.64
     in
    0.63
    관리
    0.63
     või
    0.63
    도
    0.63
    sis
    0.62
    POSITIVE LOGITS
    ل
    0.85
    ่า
    0.75
     yattha
    0.72
    มี
    0.69
    ä
    0.69
     одну
    0.68
    one
    0.66
     Appellate
    0.66
    ิบ
    0.64
     одна
    0.64
    Act Density 0.000%

    No Known Activations