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

    Neuronpedia

    INDEX
    Explanations

    safe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dividend
    -0.06
    илось
    -0.06
    fav
    -0.06
     grad
    -0.06
    atern
    -0.06
     Heading
    -0.06
    	mask
    -0.06
    LTE
    -0.06
    (gui
    -0.06
    ились
    -0.06
    POSITIVE LOGITS
    	GPIO
    0.07
    '].'
    0.06
    (red
    0.06
    程
    0.06
     erotico
    0.06
     Audi
    0.06
     resultList
    0.06
     compressor
    0.06
    peror
    0.06
     matching
    0.06
    Act Density 0.013%

    No Known Activations