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

    Neuronpedia

    INDEX
    Explanations

    Book

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rně
    -0.07
     چت
    -0.07
    []>↵
    -0.07
    .AddColumn
    -0.06
     Nhà
    -0.06
     ";↵↵
    -0.06
    (co
    -0.06
     рождения
    -0.06
       ↵↵
    -0.06
    增
    -0.06
    POSITIVE LOGITS
     Book
    0.11
    Book
    0.09
     BOOK
    0.08
     book
    0.08
     dial
    0.07
    /book
    0.06
    urum
    0.06
     Palestinian
    0.06
    book
    0.06
     kitab
    0.06
    Act Density 0.014%

    No Known Activations