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

    Neuronpedia

    INDEX
    Explanations

    library and librarian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     produk
    0.49
     prodotto
    0.48
    皿
    0.47
     devre
    0.47
     hydrophobic
    0.45
     product
    0.44
     produit
    0.43
    製品
    0.42
     productId
    0.42
     製品
    0.42
    POSITIVE LOGITS
     librarians
    2.11
     librarian
    2.00
     library
    1.99
    图书馆
    1.93
     библиоте
    1.92
     Library
    1.91
     Librarian
    1.89
    Library
    1.84
     бібліоте
    1.81
     biblioteca
    1.77
    Act Density 0.017%

    No Known Activations