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

    Neuronpedia

    INDEX
    Explanations

    references to programming tools and methods

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

    HTML heading tags (<h1>, <h2>, etc.)

    np_acts-logits-general · gemini-2.0-flash

    HTML headings and section titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -1.00
    RegressionTest
    -0.91
    Personendaten
    -0.91
    Geplaatst
    -0.91
    yntaxException
    -0.90
     gyhoeddwyd
    -0.89
    contentLoaded
    -0.86
    发表于
    -0.84
     Daß
    -0.83
    таратура
    -0.82
    POSITIVE LOGITS
    <h2>
    2.73
    <h3>
    2.33
    <h4>
    2.01
    <h1>
    1.80
    <h5>
    1.68
    <h6>
    1.36
    </h2>
    1.24
    </th>
    0.95
    </h1>
    0.94
    <strong>
    0.94
    Act Density 0.398%

    No Known Activations