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

    Neuronpedia

    INDEX
    Explanations

    references to the audience or the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    a group of people

    np_acts-logits-general · gemini-2.0-flash

    pronouns referring to groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.51
     culturelles
    -0.50
    their
    -0.47
     financieras
    -0.46
     complètes
    -0.45
    tism
    -0.44
     vœux
    -0.44
    annica
    -0.43
     aquellas
    -0.42
    HandlerContext
    -0.42
    POSITIVE LOGITS
     allemaal
    0.90
     collectively
    0.87
     all
    0.85
     guys
    0.76
     individually
    0.75
     semua
    0.73
    MigrationBuilder
    0.69
     BorderSide
    0.69
    KommentareTeilen
    0.69
     모두
    0.68
    Act Density 0.179%

    No Known Activations