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

    Neuronpedia

    INDEX
    Explanations

    mechanisms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (:,:,
    -0.09
     adjacent
    -0.08
     accesses
    -0.08
    	memcpy
    -0.08
     overlaps
    -0.07
     ngem
    -0.07
     reordered
    -0.07
     occurrences
    -0.07
     überzeug
    -0.07
     occupation
    -0.07
    POSITIVE LOGITS
     hung
    0.11
     parach
    0.10
     tether
    0.09
     telegram
    0.09
    吊
    0.09
     pend
    0.09
     Mechan
    0.09
     dangling
    0.08
     pulley
    0.08
    Mechan
    0.08
    Act Density 0.063%

    No Known Activations