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

    Neuronpedia

    INDEX
    Explanations

    say "afternoon"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tape
    -0.07
     jurisdiction
    -0.07
     کان
    -0.07
     мере
    -0.07
     regulation
    -0.06
     facility
    -0.06
     Square
    -0.06
     ordered
    -0.06
     shop
    -0.06
    traction
    -0.06
    POSITIVE LOGITS
     ซ
    0.07
    arhus
    0.07
     reusable
    0.06
    []>(
    0.06
    	JButton
    0.06
    serrat
    0.06
    @media
    0.06
    ']))
    0.06
     작성
    0.06
    inand
    0.06
    Act Density 0.094%

    No Known Activations