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

    Neuronpedia

    INDEX
    Explanations

    books

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지
    0.50
    지로
    0.47
    ف
    0.47
    지의
    0.47
     үч
    0.42
     документ
    0.41
     যাওয়ার
    0.40
    0.40
     функция
    0.39
     दौरान
    0.39
    POSITIVE LOGITS
     T
    0.61
     BOOKS
    0.59
     E
    0.59
     N
    0.59
     books
    0.56
     Y
    0.56
     Books
    0.54
     X
    0.54
     P
    0.53
    ut
    0.52
    Act Density 0.008%

    No Known Activations