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

    Neuronpedia

    INDEX
    Explanations

    basename

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    勒
    -0.07
    ycled
    -0.07
     Olymp
    -0.06
    _fh
    -0.06
    ij
    -0.06
    eries
    -0.06
    廳
    -0.06
     Diet
    -0.06
    forcing
    -0.06
     وذلك
    -0.06
    POSITIVE LOGITS
     basename
    0.09
    crop
    0.07
    abase
    0.07
     file
    0.06
    /o
    0.06
    (tmp
    0.06
     agreg
    0.06
     maximizing
    0.06
    Protocol
    0.06
    ước
    0.06
    Act Density 0.002%

    No Known Activations