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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Than
    -0.07
     printer
    -0.07
     {:.
    -0.06
     hotel
    -0.06
     rant
    -0.06
     Stark
    -0.06
    fon
    -0.06
     whore
    -0.06
    conc
    -0.06
    Recognizer
    -0.06
    POSITIVE LOGITS
     Appalach
    0.07
    pathname
    0.07
    etSocketAddress
    0.06
    ')
    0.06
     fırsat
    0.06
    父亲
    0.06
    并不
    0.06
     advisory
    0.06
    DebugEnabled
    0.06
    disable
    0.06
    Act Density 0.004%

    No Known Activations