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

    Neuronpedia

    INDEX
    Explanations

    restaurant menus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acent
    -0.07
    泊
    -0.06
    has
    -0.06
     Expr
    -0.06
     Autom
    -0.06
    CONTENT
    -0.06
     banners
    -0.06
    compat
    -0.06
     Speaking
    -0.06
    (high
    -0.06
    POSITIVE LOGITS
    inç
    0.08
     COMPLETE
    0.06
    EIF
    0.06
    .renderer
    0.06
     ніж
    0.06
     alongside
    0.06
     fired
    0.06
    Pawn
    0.06
    rün
    0.06
    罚
    0.06
    Act Density 0.034%

    No Known Activations