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

    Neuronpedia

    INDEX
    Explanations

    occurrences of underscores and their usage in data or code formatting

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

    defining data attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.45
    DockStyle
    -0.42
    berdayakan
    -0.38
    EDEFAULT
    -0.36
     ''),
    -0.36
    displayquote
    -0.36
    encodeWith
    -0.36
    __;
    -0.35
     TextAppearance
    -0.35
    FXMLLoader
    -0.35
    POSITIVE LOGITS
     factor
    0.47
     Factor
    0.46
     ショーツ
    0.46
    Reality
    0.45
    osoba
    0.44
     Truth
    0.44
     correlation
    0.43
     Theile
    0.42
    Datuak
    0.42
     Reality
    0.42
    Act Density 0.001%

    No Known Activations