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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chamber
    -0.07
    azen
    -0.07
    都知道
    -0.07
     Guidelines
    -0.07
     Trudeau
    -0.07
     Olsen
    -0.07
    tools
    -0.07
    学院
    -0.07
     Beard
    -0.06
    Tabla
    -0.06
    POSITIVE LOGITS
    <br
    0.07
     noodles
    0.07
     Radius
    0.07
    -Origin
    0.07
    長い
    0.07
    (cursor
    0.07
    	trace
    0.07
    spirit
    0.07
     Nearly
    0.07
    生活环境
    0.06
    Act Density 0.029%

    No Known Activations