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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used for quotations and block formatting

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

    HTML heading tags (h1-h6) or quotation mark-like characters

    np_acts-logits-general · gemini-2.0-flash

    user mentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bezeichneter
    -1.05
     المعيارى
    -1.01
    ollectionView
    -0.91
    stdc
    -0.88
    Personendaten
    -0.88
    mybatisplus
    -0.85
    orianCalendar
    -0.85
    =$?
    -0.84
    Amicalement
    -0.83
    multer
    -0.83
    POSITIVE LOGITS
    <blockquote>
    1.73
    </blockquote>
    1.20
    <h5>
    1.10
    <h3>
    1.03
    <h4>
    1.02
    <h1>
    0.94
    <em>
    0.92
    ↵
    0.92
    <h6>
    0.85
    ↵↵↵
    0.84
    Act Density 0.014%

    No Known Activations