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
     buckets
    -0.07
     White
    -0.07
     photographs
    -0.06
     gle
    -0.06
     inviting
    -0.06
     aggregates
    -0.06
     fran
    -0.06
    ्पन
    -0.06
     Tarihi
    -0.06
     settle
    -0.06
    POSITIVE LOGITS
     unintended
    0.08
     dereg
    0.07
    Wiki
    0.07
    	Path
    0.07
    ीए
    0.07
     nêu
    0.07
     nouvel
    0.07
    ΙΤ
    0.06
    Tại
    0.06
     موفق
    0.06
    Act Density 0.087%

    No Known Activations