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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ictim
    -0.07
     degrade
    -0.06
     są
    -0.06
    ITHER
    -0.06
    游戏玩家
    -0.06
     niños
    -0.06
    提升
    -0.06
     várias
    -0.06
    香港
    -0.06
     raster
    -0.06
    POSITIVE LOGITS
    ewis
    0.07
    lland
    0.07
    _appro
    0.07
    بر
    0.07
    john
    0.07
     Sears
    0.07
    ewart
    0.07
    ি
    0.07
     viewWillAppear
    0.07
     Parts
    0.07
    Act Density 0.044%

    No Known Activations