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

    Neuronpedia

    INDEX
    Explanations

    interfaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surfaces
    -1.03
     pages
    -0.94
     interfaces
    -0.66
     Surfaces
    -0.65
     slides
    -0.65
    Pages
    -0.60
     Pages
    -0.60
     quantity
    -0.59
    surfaces
    -0.59
     L
    -0.54
    POSITIVE LOGITS
     étanche
    0.79
     aikaa
    0.79
    IsContent
    0.78
     présentes
    0.76
     composés
    0.76
    seamnă
    0.76
     variés
    0.75
     vulné
    0.75
     dieux
    0.73
     élevés
    0.73
    Act Density 0.078%

    No Known Activations