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

    Neuronpedia

    INDEX
    Explanations

    the definite article "the" followed by country names and abbreviations, especially "the UK" and "the US"

    oai_token-act-pair · gemini-2.0-flash

    foreign language tokens or non-English text

    np_token-act-pair-logits · gpt-4o-mini

    say "the [country]"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verksam
    -0.41
    kirakan
    -0.41
    多种
    -0.41
    träglich
    -0.39
     stället
    -0.39
     GENERATED
    -0.38
    urllib
    -0.38
    路
    -0.38
     löyty
    -0.38
    リュ
    -0.38
    POSITIVE LOGITS
    OGND
    0.90
    исленность
    0.88
    oredCriteria
    0.84
    Personensuche
    0.84
     виправивши
    0.77
    脚注の使い方
    0.75
     >=",
    0.72
    دانشنامهٔ
    0.69
    MessageTagHelper
    0.69
    IsMutable
    0.69
    Act Density 0.654%

    No Known Activations