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

    Neuronpedia

    INDEX
    Explanations

    references to web pages, countries, and families

    oai_token-act-pair · gemini-2.0-flash

    countries or web pages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EconPapers
    -1.02
    spesies
    -0.67
     vice
    -0.66
    UnusedPrivate
    -0.65
     فريبيس
    -0.64
     Numerade
    -0.64
    newswire
    -0.63
    canestro
    -0.62
     Utf
    -0.62
    énario
    -0.62
    POSITIVE LOGITS
    #
    0.60
     aici
    0.59
    <bos>
    0.57
     aquí
    0.53
     тук
    0.52
     noastre
    0.52
    interopRequire
    0.52
     razão
    0.52
     Dumnezeu
    0.51
     Ponce
    0.51
    Act Density 0.631%

    No Known Activations