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

    Neuronpedia

    INDEX
    Explanations

    words appearing across a variety of technical and scientific documents

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ***!
    -0.75
    verwijspagina
    -0.63
    /***/
    -0.59
     المعيارى
    -0.56
     (;;)
    -0.56
    údo
    -0.54
    leyeb
    -0.54
    liyor
    -0.54
    gypte
    -0.52
    potamus
    -0.50
    POSITIVE LOGITS
     <>",
    0.70
    IUrlHelper
    0.57
     initComponents
    0.55
     FetchType
    0.50
     Auflage
    0.50
     useContext
    0.48
     Cinque
    0.48
     einz
    0.46
     useStyles
    0.43
     Ratchet
    0.43
    Act Density 3.549%

    No Known Activations