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

    Neuronpedia

    INDEX
    Explanations

    obligatory comments/links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     페이지
    -0.07
     Lionel
    -0.07
    ersonic
    -0.07
     nu
    -0.06
     Sat
    -0.06
    _integer
    -0.06
     Muk
    -0.06
     Lyn
    -0.06
     جي
    -0.06
     Southeast
    -0.06
    POSITIVE LOGITS
     *,↵
    0.06
     wow
    0.06
     __________________________________
    0.06
    ch
    0.06
     leases
    0.06
    Clickable
    0.06
     Username
    0.06
     antlr
    0.06
    _re
    0.06
    ähl
    0.05
    Act Density 0.000%

    No Known Activations