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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements commonly used in programming or code snippets

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

    programming language elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.82
    aarrggbb
    -0.81
     Chwiliwch
    -0.76
    AddTagHelper
    -0.70
    Parcelize
    -0.69
    MLLoader
    -0.68
    ThroughAttribute
    -0.68
     AssemblyCompany
    -0.68
    WebServlet
    -0.68
     pinulongan
    -0.68
    POSITIVE LOGITS
     began
    0.43
     proceeded
    0.36
     begin
    0.32
     evening
    0.32
     beginning
    0.32
     started
    0.32
     slowly
    0.32
    ARROLLO
    0.31
     smooth
    0.31
     comenzó
    0.31
    Act Density 0.014%

    No Known Activations