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

    Neuronpedia

    INDEX
    Explanations

    references to contracts and their terms

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

    Preceding words like "the", "in", "of", "it"

    np_acts-logits-general · gemini-2.0-flash

    true, actual, factual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.58
    MigrationBuilder
    -0.54
    +#+#
    -0.51
    unsqueeze
    -0.51
    ArrowToggle
    -0.50
    udahan
    -0.49
    <bos>
    -0.49
    yntaxException
    -0.46
     snippetHide
    -0.44
    жалуйста
    -0.44
    POSITIVE LOGITS
     verdadera
    2.52
     true
    2.44
     verdadero
    2.43
     véritable
    2.42
     truly
    2.37
    真正的
    2.30
     vrai
    2.29
    真正
    2.23
     actual
    2.22
     vraie
    2.21
    Act Density 0.808%

    No Known Activations