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

    Neuronpedia

    INDEX
    Explanations

    science and economics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sphinx
    -0.07
     ()↵
    -0.06
     CART
    -0.06
    スティ
    -0.06
    Root
    -0.06
     اث
    -0.06
     Dex
    -0.06
     roli
    -0.06
    r
    -0.06
     billeder
    -0.06
    POSITIVE LOGITS
    size
    0.08
    	size
    0.07
    _SIZE
    0.07
    pedo
    0.07
     ordin
    0.07
     Algebra
    0.07
    -Encoding
    0.07
    <vector
    0.07
    \"><
    0.07
    sector
    0.07
    Act Density 0.032%

    No Known Activations