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

    Neuronpedia

    INDEX
    Explanations

    nutrition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scraping
    -0.08
     probing
    -0.08
    usses
    -0.07
     pressing
    -0.07
     ating
    -0.07
    udge
    -0.07
     indis
    -0.07
     dérou
    -0.07
     knowledgeable
    -0.07
     opinions
    -0.07
    POSITIVE LOGITS
        	↵
    0.08
    লাই
    0.08
            ↵↵
    0.08
     trotz
    0.07
    	counter
    0.07
     communion
    0.07
     नस
    0.07
    hog
    0.07
    	lib
    0.07
    	java
    0.07
    Act Density 0.001%

    No Known Activations