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
    TURE
    -0.07
     liebe
    -0.07
    Partial
    -0.06
    CALE
    -0.06
     exploring
    -0.06
     alone
    -0.06
    _TYPE
    -0.06
     FORCE
    -0.06
     activating
    -0.06
    _KIND
    -0.06
    POSITIVE LOGITS
     Produkte
    0.07
     Cir
    0.06
    ipher
    0.06
     Beaver
    0.06
     Федераль
    0.06
    etik
    0.06
     Además
    0.06
     primera
    0.06
     星
    0.06
     publik
    0.06
    Act Density 0.136%

    No Known Activations