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

    Neuronpedia

    INDEX
    Explanations

    Counter arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	assertEquals
    -0.07
     点击
    -0.07
     Peel
    -0.07
    ptest
    -0.06
    edges
    -0.06
     bgColor
    -0.06
    LEMENT
    -0.06
    370
    -0.06
    LEE
    -0.06
    essler
    -0.06
    POSITIVE LOGITS
     onComplete
    0.06
    спіль
    0.06
    _winner
    0.06
    _general
    0.06
    InputDialog
    0.06
     straw
    0.06
    _Max
    0.06
     deterrent
    0.06
     slap
    0.06
     construed
    0.05
    Act Density 0.119%

    No Known Activations