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

    Neuronpedia

    INDEX
    Explanations

    Holy Roman Empire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     \$
    -0.08
    切
    -0.08
     proporcional
    -0.08
     diferenci
    -0.07
     manga
    -0.07
    rás
    -0.07
     Swansea
    -0.07
     driven
    -0.07
     blitz
    -0.07
    incy
    -0.07
    POSITIVE LOGITS
     medieval
    0.10
    вание
    0.09
    egg
    0.08
     elections
    0.08
    Karl
    0.08
     Emperor
    0.08
    wain
    0.08
     Karl
    0.08
     elected
    0.08
    	version
    0.08
    Act Density 0.003%

    No Known Activations