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

    Neuronpedia

    INDEX
    Explanations

    occurrences of input/output statements in programming code

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

    print statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.50
    AccessorTable
    -0.44
    Datuak
    -0.43
    PyExc
    -0.43
    -0.43
     Wikimedijinoj
    -0.42
    ␮
    -0.42
    AddTagHelper
    -0.42
    omiast
    -0.42
    rafo
    -0.41
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.48
    ArgumentParser
    0.44
     CWE
    0.43
     betweenstory
    0.43
    erçe
    0.43
     Duro
    0.42
    mence
    0.42
     createState
    0.42
    nEnter
    0.40
    чень
    0.39
    Act Density 0.002%

    No Known Activations