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

    Neuronpedia

    INDEX
    Explanations

    Code/file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (buf
    -0.07
    想过
    -0.07
    amen
    -0.07
     {(
    -0.07
    냏
    -0.07
     atau
    -0.07
     Scholars
    -0.06
    diğiniz
    -0.06
     Andre
    -0.06
    Explore
    -0.06
    POSITIVE LOGITS
     حص
    0.07
    addColumn
    0.06
     Dimension
    0.06
    StartPosition
    0.06
     wat
    0.06
    很低
    0.06
    冻
    0.06
    кат
    0.06
    Await
    0.06
    	player
    0.06
    Act Density 0.022%

    No Known Activations