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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     authoritarian
    -0.07
    Rooms
    -0.07
    None
    -0.07
    xCF
    -0.07
    _LOWER
    -0.06
    Css
    -0.06
     seating
    -0.06
    .Default
    -0.06
    "...
    -0.06
    497
    -0.06
    POSITIVE LOGITS
     بع
    0.07
     pra
    0.06
     sent
    0.06
     dub
    0.06
    	widget
    0.06
    	filename
    0.06
    Za
    0.06
     overlooking
    0.06
    لس
    0.06
    (to
    0.06
    Act Density 0.018%

    No Known Activations