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

    Neuronpedia

    INDEX
    Explanations

    references to special organizations or initiatives

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

    special preceding nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.69
    SourceChecksum
    -0.52
    UnitTesting
    -0.51
    vro
    -0.48
    abestanden
    -0.48
    AnimationsModule
    -0.47
    んぼ
    -0.45
     oprot
    -0.45
    şört
    -0.45
     Mombasa
    -0.44
    POSITIVE LOGITS
     special
    0.71
     Special
    0.57
    特別
    0.56
    special
    0.54
    Special
    0.50
     especiais
    0.50
     spécial
    0.49
     especial
    0.48
     ویژه
    0.48
     spéciaux
    0.47
    Act Density 0.004%

    No Known Activations