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

    Neuronpedia

    INDEX
    Explanations

    references to books and their attributes or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    about books

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vrijwilli
    -0.52
     казалось
    -0.48
     terecht
    -0.48
    USTOM
    -0.47
    ValueGeneration
    -0.46
    prefixer
    -0.45
     mogen
    -0.45
     batas
    -0.44
    idden
    -0.44
     bezpeč
    -0.42
    POSITIVE LOGITS
     book
    0.99
     books
    0.96
     bookId
    0.82
     Book
    0.81
    Book
    0.79
    Books
    0.76
    books
    0.75
     Books
    0.74
     livro
    0.74
     boken
    0.71
    Act Density 0.029%

    No Known Activations