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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intent and clarification

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

    clarification or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    declare
    -0.47
    OCCURRED
    -0.39
     declared
    -0.38
    yki
    -0.37
    cookieParser
    -0.37
     declaring
    -0.35
    exitRule
    -0.35
    RuleContext
    -0.35
     conso
    -0.35
    goi
    -0.35
    POSITIVE LOGITS
    tagHelperRunner
    0.61
     Simultaneous
    0.56
    findpost
    0.54
    Simult
    0.49
    utnik
    0.47
     autorytatywna
    0.46
     ketat
    0.46
    الصفحه
    0.45
    Serious
    0.42
    뀜
    0.42
    Act Density 0.149%

    No Known Activations