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

    Neuronpedia

    INDEX
    Explanations

    code punctuation/numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dân
    -0.07
    tram
    -0.07
    داری
    -0.07
    handles
    -0.06
     soruml
    -0.06
    стика
    -0.06
     delayed
    -0.06
     सद
    -0.06
    чі
    -0.06
     savun
    -0.06
    POSITIVE LOGITS
     fees
    0.07
    كييف
    0.06
    @author
    0.06
     useMemo
    0.06
     patter
    0.06
    /testify
    0.06
    (disposing
    0.06
    Jamie
    0.06
    upply
    0.06
     Woody
    0.06
    Act Density 0.004%

    No Known Activations