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

    Neuronpedia

    INDEX
    Explanations

    primary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     उद्ध
    -0.08
     piste
    -0.08
    âng
    -0.08
     movie
    -0.08
     sache
    -0.07
    -Date
    -0.07
     bullets
    -0.07
     المؤ
    -0.07
     Xamarin
    -0.07
     scholarships
    -0.07
    POSITIVE LOGITS
     cortex
    0.10
     konuş
    0.09
     lect
    0.09
     kain
    0.09
     neighborhoods
    0.09
     elo
    0.08
     пров
    0.08
     receptive
    0.08
     புர
    0.08
    Regions
    0.08
    Act Density 0.004%

    No Known Activations