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

    Neuronpedia

    INDEX
    Explanations

    lengthy sequences of uninterrupted whitespace or indentation in the text

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

    programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ffilmiau
    -0.41
    DebuggerStep
    -0.39
    KURZBESCHREIBUNG
    -0.39
     مرئيه
    -0.39
    CURLOPT
    -0.39
    putString
    -0.37
    ollectionView
    -0.36
     Dino
    -0.36
    JsonPropertyName
    -0.35
    AddTagHelper
    -0.35
    POSITIVE LOGITS
    initComponents
    1.41
     toekomst
    0.54
    MessageOf
    0.48
    IsMutable
    0.48
     ویکی‌پدی
    0.48
     ExecuteAsync
    0.47
     resourceCulture
    0.46
    rawDesc
    0.46
    parsedMessage
    0.45
     iprot
    0.45
    Act Density 0.001%

    No Known Activations