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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucas
    -0.07
    prak
    -0.07
    endl
    -0.06
     ве
    -0.06
     Wi
    -0.06
     fiction
    -0.06
     näch
    -0.06
    .index
    -0.06
     quick
    -0.06
     convey
    -0.06
    POSITIVE LOGITS
    #
    0.08
    сім
    0.07
     Sultan
    0.07
    #__
    0.07
    fab
    0.06
    (constants
    0.06
     باشگاه
    0.06
     +#
    0.06
     Instruments
    0.06
    'nde
    0.06
    Act Density 0.004%

    No Known Activations