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

    Neuronpedia

    INDEX
    Explanations

    headings and formatting elements in text

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

    roman numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    قایناقلار
    -0.72
    parsedMessage
    -0.69
     المعيارى
    -0.64
     Audiodateien
    -0.63
     ſind
    -0.63
     kasarigan
    -0.63
     iconFacebook
    -0.63
     betweenstory
    -0.63
    majánló
    -0.60
     تضيفلها
    -0.60
    POSITIVE LOGITS
     corners
    0.37
     meet
    0.35
     true
    0.34
    <h2>
    0.34
     corner
    0.34
    ↵
    0.34
    )
    0.33
     $
    0.33
     new
    0.32
     his
    0.32
    Act Density 0.000%

    No Known Activations