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

    Neuronpedia

    INDEX
    Explanations

    instances of opening and closing parentheses

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

    print statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.78
     يتيمه
    -0.75
     queſta
    -0.71
     Италијани
    -0.70
    fjspx
    -0.68
    complexContent
    -0.65
     noDo
    -0.62
    yntaxException
    -0.62
     ujednoznacz
    -0.60
    RenderAtEndOf
    -0.60
    POSITIVE LOGITS
    WriteLine
    0.60
    println
    0.49
    Println
    0.46
    print
    0.40
     diversidad
    0.40
     múltiple
    0.39
     Italij
    0.38
     leçon
    0.37
     república
    0.36
    <>(
    0.36
    Act Density 0.002%

    No Known Activations