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

    Neuronpedia

    INDEX
    Explanations

    code or configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ursos
    -0.06
    Af
    -0.06
    通知
    -0.06
    加工
    -0.06
    -sup
    -0.06
    泽
    -0.06
     cuz
    -0.06
    	ERROR
    -0.06
     invention
    -0.06
     Convers
    -0.06
    POSITIVE LOGITS
    онах
    0.07
    盘
    0.07
     seriously
    0.07
    .GetBytes
    0.07
    .items
    0.06
    ecc
    0.06
    atings
    0.06
    estination
    0.06
    -main
    0.06
    .FONT
    0.06
    Act Density 0.013%

    No Known Activations