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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marrying
    -0.06
     latitude
    -0.06
    jl
    -0.06
     supp
    -0.06
    GX
    -0.06
     prav
    -0.06
     downloaded
    -0.06
     Albany
    -0.06
    known
    -0.06
    inside
    -0.06
    POSITIVE LOGITS
     Kons
    0.07
    USIC
    0.07
    InMillis
    0.06
    ινων
    0.06
     OF
    0.06
     Continental
    0.06
    /admin
    0.06
     annex
    0.06
     eines
    0.06
    customers
    0.06
    Act Density 0.038%

    No Known Activations