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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     _$
    -0.73
     Numerade
    -0.67
     للاسماء
    -0.66
    FieldOffset
    -0.65
     незавершена
    -0.65
     MainAxisSize
    -0.65
     defaultstate
    -0.62
    NameInMap
    -0.61
     IFT
    -0.61
     Wicidata
    -0.61
    POSITIVE LOGITS
     are
    0.63
     is
    0.63
    info
    0.54
    AutoScale
    0.53
     of
    0.52
     have
    0.52
     has
    0.52
    is
    0.50
    find
    0.49
    text
    0.47
    Act Density 0.015%

    No Known Activations