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

    Neuronpedia

    INDEX
    Explanations

    conversation and dialogue in informal contexts

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

    Following punctuation or discourse markers in various languages

    np_acts-logits-general · gemini-2.0-flash

    conversational phrases across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagHelper
    -0.72
    Together
    -0.59
    WebElementEntity
    -0.59
    éndose
    -0.58
    éndolo
    -0.58
    ～」
    -0.58
    éndole
    -0.57
     Together
    -0.53
    (©
    -0.53
     niyang
    -0.52
    POSITIVE LOGITS
     ویکی‌پدی
    0.61
     سكانية
    0.57
    CodeAttribute
    0.56
     jurídica
    0.54
    UnitTesting
    0.54
    MemoryWarning
    0.54
    StandardCharsets
    0.53
    Pardon
    0.53
     Euphrates
    0.53
    MEMORANDUM
    0.53
    Act Density 0.137%

    No Known Activations