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

    Neuronpedia

    INDEX
    Explanations

    function definitions and control flow structures in programming code

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

    foreign languages and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.51
    :✨
    -0.49
    AutoModerator
    -0.44
     faſt
    -0.43
     stork
    -0.42
    protoimpl
    -0.41
    Parcelize
    -0.41
     pymysql
    -0.41
     CommonModule
    -0.41
    FromNib
    -0.40
    POSITIVE LOGITS
    MemoryWarning
    0.51
     يتيمه
    0.49
    XtraReports
    0.43
    msgTypes
    0.40
     propOrder
    0.40
     Савезне
    0.40
    ună
    0.39
    Quellen
    0.39
     المعيارى
    0.39
     OMITBAD
    0.39
    Act Density 0.012%

    No Known Activations