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

    Neuronpedia

    INDEX
    Explanations

    door

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ughters
    -0.07
    Clark
    -0.07
     Ash
    -0.06
     SPORT
    -0.06
    ISION
    -0.06
    ipation
    -0.06
    safe
    -0.06
    	main
    -0.06
     cleared
    -0.06
    Notice
    -0.06
    POSITIVE LOGITS
     аг
    0.07
    (Collider
    0.07
     kola
    0.07
     hWnd
    0.07
     verk
    0.07
    '{
    0.06
     okum
    0.06
    лор
    0.06
     žid
    0.06
     llen
    0.06
    Act Density 0.009%

    No Known Activations