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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	display
    -0.07
    (Constructor
    -0.07
     Wells
    -0.06
     bilin
    -0.06
     MARK
    -0.06
     châu
    -0.06
    .WebElement
    -0.06
    ocks
    -0.06
     abl
    -0.06
    ponent
    -0.06
    POSITIVE LOGITS
    resse
    0.07
    Past
    0.07
             ↵
    0.06
     DO
    0.06
    NotFoundError
    0.06
    asing
    0.06
              ↵
    0.06
    둥
    0.06
     fraternity
    0.06
     }↵
    0.06
    Act Density 0.390%

    No Known Activations