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

    Neuronpedia

    INDEX
    Explanations

    Choosing and obtaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defs
    -0.07
    interop
    -0.07
    Compilation
    -0.06
    Region
    -0.06
     rects
    -0.06
    bies
    -0.06
    	nil
    -0.06
    Grid
    -0.06
    direction
    -0.06
    _outputs
    -0.06
    POSITIVE LOGITS
     shaft
    0.06
     weaken
    0.06
    ẳn
    0.06
     Milit
    0.06
     wager
    0.06
     العالمية
    0.06
     WEEK
    0.06
     hư
    0.06
     تلویزیون
    0.06
     시
    0.05
    Act Density 0.337%

    No Known Activations