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

    Neuronpedia

    INDEX
    Explanations

    references to publications and the frequency of their mention in texts

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

    kinds of publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aéro
    -0.52
     démocr
    -0.50
     chré
    -0.50
     colère
    -0.47
     fédé
    -0.47
     Connectez
    -0.47
    setMin
    -0.46
    <bos>
    -0.46
    lazy
    -0.46
     météo
    -0.46
    POSITIVE LOGITS
     Publication
    1.00
    Publication
    0.99
     publication
    0.98
     Publications
    0.92
    publication
    0.92
    Publications
    0.88
     publications
    0.82
     PUBLICATIONS
    0.81
     PUBLICATION
    0.79
    publications
    0.65
    Act Density 0.006%

    No Known Activations