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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     но
    -0.08
     Dresden
    -0.07
     phần
    -0.06
    _except
    -0.06
    <<"\
    -0.06
     *>(
    -0.06
    uppet
    -0.06
    resden
    -0.06
    Inicio
    -0.06
     svaz
    -0.06
    POSITIVE LOGITS
     mond
    0.07
    nick
    0.07
    fur
    0.06
    coal
    0.06
    zoom
    0.06
    	element
    0.06
    .parseColor
    0.06
    ICATION
    0.06
    arie
    0.06
     Jasper
    0.06
    Act Density 0.020%

    No Known Activations