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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and related grammatical structures

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.63
     unknownFields
    -0.53
    出版年
    -0.52
    中略
    -0.49
    TagHelper
    -0.47
     OMITTED
    -0.47
     بيها
    -0.46
     manches
    -0.46
    guarantee
    -0.46
    mangle
    -0.46
    POSITIVE LOGITS
    これも
    0.71
    それも
    0.64
    Portály
    0.62
    <eos>
    0.62
     kasarigan
    0.60
    GTCX
    0.58
    তথ্যসূত্র
    0.58
    こちらも
    0.55
    הערות
    0.55
     taip
    0.54
    Act Density 0.388%

    No Known Activations