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

    Neuronpedia

    INDEX
    Explanations

    titles and headings related to updates or new features in a newsletter or blog format

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

    HTML heading tags

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "),
    -1.82
    ),"
    -1.67
    ")
    -1.57
    )",
    -1.52
    ").
    -1.50
    ),
    -1.44
    ."),
    -1.32
    )"),
    -1.29
    ”),
    -1.28
    ),”
    -1.26
    POSITIVE LOGITS
    </h4>
    3.91
    <h4>
    2.30
    </h6>
    1.97
    </sup>
    1.58
    </h3>
    1.56
    </blockquote>
    1.54
    </h5>
    1.48
    </th>
    1.38
    】
    1.30
    <h5>
    1.29
    Act Density 0.137%

    No Known Activations