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

    Neuronpedia

    INDEX
    Explanations

    Films/Performing Arts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reefs
    -0.06
    _NOP
    -0.06
    UDO
    -0.06
    制作
    -0.06
    urations
    -0.06
     соверш
    -0.06
     krist
    -0.06
     حسن
    -0.06
     pragma
    -0.06
    udder
    -0.05
    POSITIVE LOGITS
     effic
    0.08
    COOKIE
    0.07
     цін
    0.07
     Федерации
    0.07
     hind
    0.07
     format
    0.07
     ******************************************************************************/↵
    0.06
    111
    0.06
    milliseconds
    0.06
     sexism
    0.06
    Act Density 0.045%

    No Known Activations