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
    ndata
    -0.07
    >f
    -0.07
     allergies
    -0.07
     fw
    -0.07
    idges
    -0.06
     fright
    -0.06
     RF
    -0.06
    -Core
    -0.06
    rection
    -0.06
     HOLDER
    -0.06
    POSITIVE LOGITS
     همین
    0.07
     včetně
    0.06
     salute
    0.06
     Flickr
    0.06
    	Random
    0.06
    Whatever
    0.06
     tremend
    0.06
    (server
    0.06
     catastrophic
    0.06
    +#
    0.06
    Act Density 0.000%

    No Known Activations