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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rpt
    -0.07
     vur
    -0.07
     ;↵↵
    -0.07
     prince
    -0.07
     ואף
    -0.07
     indikator
    -0.07
    个位
    -0.07
     glo
    -0.07
    -End
    -0.07
     самостоятельно
    -0.07
    POSITIVE LOGITS
    leading
    0.08
    azos
    0.08
     withholding
    0.07
    straight
    0.07
     tập
    0.07
     bondage
    0.07
     ظهر
    0.07
    az
    0.07
    azy
    0.07
     YMCA
    0.07
    Act Density 0.004%

    No Known Activations