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

    Neuronpedia

    INDEX
    Explanations

    code, math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    к
    -0.07
    xs
    -0.06
     ErrorHandler
    -0.06
    inker
    -0.06
    Boom
    -0.06
    _portal
    -0.06
    кин
    -0.06
    ifica
    -0.06
     filmed
    -0.06
    >No
    -0.06
    POSITIVE LOGITS
     transcript
    0.07
     자동
    0.07
    握
    0.07
     جای
    0.06
    ))+
    0.06
     поверхности
    0.06
     gösteren
    0.06
     carpet
    0.06
     Displays
    0.06
     pizzas
    0.06
    Act Density 0.031%

    No Known Activations