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

    Neuronpedia

    INDEX
    Explanations

    library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     library
    -2.59
    library
    -2.23
     Library
    -2.20
    Library
    -2.11
     LIBRARY
    -2.08
     libraries
    -2.06
     Libraries
    -1.80
    LIBRARY
    -1.80
     biblioteca
    -1.76
     bibliothèque
    -1.72
    POSITIVE LOGITS
     of
    0.60
    .
    0.54
    of
    0.51
    ,
    0.48
     né
    0.45
    rawDesc
    0.45
    ette
    0.45
    bs
    0.45
    락
    0.44
    شی
    0.44
    Act Density 0.100%

    No Known Activations