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

    Neuronpedia

    INDEX
    Explanations

    removing redundant phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的な
    0.46
    Proposition
    0.45
    INR
    0.43
    шымта
    0.42
     स्टोक्स
    0.41
    ନ୍ଦ
    0.41
    𝗷
    0.41
     값을
    0.40
    ₹
    0.40
     নিক
    0.39
    POSITIVE LOGITS
     des
    0.53
    Теперь
    0.49
     kỷ
    0.48
    。
    0.46
     tăng
    0.46
     im
    0.45
     mehr
    0.45
     modifier
    0.44
    dı
    0.44
     Modifier
    0.44
    Act Density 0.007%

    No Known Activations