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

    Neuronpedia

    INDEX
    Explanations

    notice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ден
    -0.07
    cant
    -0.07
    (vals
    -0.06
    Roy
    -0.06
    ISA
    -0.06
     sell
    -0.06
     IPT
    -0.06
     Rog
    -0.06
    	AT
    -0.06
    commended
    -0.06
    POSITIVE LOGITS
     errorCode
    0.06
     isten
    0.06
    _gettime
    0.06
     rocked
    0.06
    luv
    0.06
     personel
    0.06
    paren
    0.06
     producto
    0.06
     lobbyists
    0.06
    -str
    0.06
    Act Density 0.001%

    No Known Activations