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

    Neuronpedia

    INDEX
    Explanations

    expressions of disagreement or contradiction

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

    Follows a digit

    np_acts-logits-general · gemini-2.0-flash

    numbers and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.96
    الحياه
    -0.90
    sizeCache
    -0.89
    setof
    -0.84
    Билгалдахарш
    -0.80
    جغرافيا
    -0.78
    Portail
    -0.78
    balleur
    -0.78
     Wikispecies
    -0.77
    Datuak
    -0.77
    POSITIVE LOGITS
    </blockquote>
    0.50
    </td>
    0.45
    </h4>
    0.42
     فريبيس
    0.41
    </h1>
    0.41
    </h6>
    0.41
    [toxicity=0]
    0.40
     <<<<<<<<<<<<<<
    0.38
    徊
    0.38
    ↵
    0.37
    Act Density 0.779%

    No Known Activations