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

    Neuronpedia

    INDEX
    Explanations

    special character sequences and keywords in technical or programming contexts

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

    code and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Suiza
    -0.33
     llegar
    -0.33
     Baumann
    -0.31
     quedando
    -0.30
     dont
    -0.30
     navidad
    -0.30
     permitan
    -0.30
     lunes
    -0.29
     tambien
    -0.29
     quedaba
    -0.28
    POSITIVE LOGITS
     PropTypes
    0.95
    webElementGuid
    0.67
     ब्रेकडाउन
    0.65
     bookId
    0.63
    homonymie
    0.63
    matchCondition
    0.60
    ésultats
    0.60
    󠁬
    0.58
    [@BOS@]
    0.57
    <unused41>
    0.57
    Act Density 0.001%

    No Known Activations