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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     umbrella
    -0.08
     sweep
    -0.08
    wy
    -0.07
    	sum
    -0.07
     wipe
    -0.07
    yp
    -0.06
    +"
    -0.06
     clearly
    -0.06
     overlay
    -0.06
    Imp
    -0.06
    POSITIVE LOGITS
    ")↵
    0.17
    ");↵
    0.15
    ')↵
    0.15
    ');↵
    0.13
    ")↵↵
    0.12
    ");↵↵
    0.12
    ')↵↵
    0.11
    "]↵
    0.10
    ');↵↵
    0.10
     ")↵
    0.10
    Act Density 0.108%

    No Known Activations