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

    Neuronpedia

    INDEX
    Explanations

    problem, question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMP
    -0.07
    ...",↵
    -0.06
    Date
    -0.06
     Europeans
    -0.06
    очно
    -0.06
    就是
    -0.06
    وده
    -0.06
    Watch
    -0.06
     periodo
    -0.06
     cultivated
    -0.06
    POSITIVE LOGITS
    	glEnable
    0.06
     offen
    0.06
     στα
    0.06
     congrat
    0.06
     sidelined
    0.06
     nebyla
    0.06
     irre
    0.06
     Closet
    0.06
     disguised
    0.06
     Unicode
    0.06
    Act Density 0.062%

    No Known Activations