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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Add
    -0.06
    _TRACK
    -0.06
    Album
    -0.06
     Kunst
    -0.06
    stanbul
    -0.06
     Tou
    -0.06
    閉
    -0.06
    itzer
    -0.06
     vertically
    -0.06
     Walt
    -0.06
    POSITIVE LOGITS
     produces
    0.07
     graduation
    0.07
    lbs
    0.07
    \",↵
    0.07
     networking
    0.07
     exponent
    0.07
    msgs
    0.07
     '"';↵
    0.06
     destroys
    0.06
    HTTPS
    0.06
    Act Density 0.000%

    No Known Activations