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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.68
    VersionUID
    -0.68
    BagConstraints
    -0.65
    UrlResolution
    -0.64
    rrggbb
    -0.64
     Lightboxes
    -0.60
    writerow
    -0.60
    uxxxx
    -0.60
    AndEndTag
    -0.60
    CloseOperation
    -0.59
    POSITIVE LOGITS
     propOrder
    0.51
     giusti
    0.46
     rojos
    0.46
     GIFs
    0.45
     CMC
    0.44
     GSC
    0.44
     FSC
    0.44
     useStyles
    0.42
     PIS
    0.42
     GMA
    0.42
    Act Density 0.003%

    No Known Activations