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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     columnHeader
    -0.07
    gre
    -0.06
    100
    -0.06
    namespace
    -0.06
    .Orientation
    -0.06
    LLLL
    -0.06
    .Act
    -0.06
     Outer
    -0.06
    	holder
    -0.06
    aac
    -0.06
    POSITIVE LOGITS
    ...(
    0.08
     Fetish
    0.07
    ideas
    0.07
    Snap
    0.06
    ">${
    0.06
     стран
    0.06
     danmark
    0.06
    ）
↵
    0.06
    useState
    0.06
     역사
    0.06
    Act Density 0.325%

    No Known Activations