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

    Neuronpedia

    INDEX
    Explanations

    foundation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.68
    )|^{
    -0.53
    ihnachten
    -0.52
    TagHelper
    -0.52
    ergic
    -0.51
    enumii
    -0.51
    링
    -0.49
    tably
    -0.48
    JPL
    -0.46
     Савез
    -0.46
    POSITIVE LOGITS
     of
    2.02
     của
    0.89
    ของ
    0.85
    of
    0.74
     ofthe
    0.71
     thereof
    0.70
     toho
    0.66
     των
    0.65
     for
    0.65
    ofa
    0.65
    Act Density 0.055%

    No Known Activations