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

    Neuronpedia

    INDEX
    Explanations

    questions related to reason and justification

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

    Comes after question words

    np_acts-logits-general · gemini-2.0-flash

    not least or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.54
    NameInMap
    -0.47
    Cordialement
    -0.46
    migrationBuilder
    -0.45
    ValueStyle
    -0.42
     Biôgrafia
    -0.41
     Comprometido
    -0.40
    Rüyada
    -0.40
     linkovi
    -0.40
    ToDouble
    -0.39
    POSITIVE LOGITS
    interopRequire
    0.43
    ImageContext
    0.39
     cuarent
    0.37
    SharedDtor
    0.36
    ConverterFactory
    0.34
    Immediately
    0.34
    lessons
    0.33
     montón
    0.33
    setupUi
    0.33
     Drury
    0.32
    Act Density 0.534%

    No Known Activations