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

    Neuronpedia

    INDEX
    Explanations

    contractions indicating negation

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

    Apostrophes at the end of words

    np_acts-logits-general · gemini-2.0-flash

    follows punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Референце
    -0.72
     beginnetje
    -0.72
     lenker
    -0.71
    Πηγές
    -0.71
    )++;
    -0.69
    зулта
    -0.68
    setof
    -0.66
    Personensuche
    -0.66
    sizeCache
    -0.65
    ^(@)
    -0.64
    POSITIVE LOGITS
    [toxicity=0]
    0.77
    <strong>
    0.72
    </blockquote>
    0.67
    </h6>
    0.62
    <h2>
    0.62
    例文帳に追加
    0.62
    </td>
    0.60
    <sup>
    0.59
    ↵↵
    0.58
    <b>
    0.56
    Act Density 0.671%

    No Known Activations