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

    Neuronpedia

    INDEX
    Explanations

    words near prepositions, book titles, and author names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wiktionnaire
    -0.59
    Rhestr
    -0.58
    <bos>
    -0.54
    tvguidetime
    -0.51
    usercontent
    -0.50
    IsContent
    -0.50
    HasBeenSet
    -0.49
     Homeless
    -0.49
     rhestr
    -0.48
    dibles
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.54
     AttributeSet
    0.50
     ?>
    0.47
     Qaraldi
    0.47
    scriptcase
    0.46
    fuls
    0.46
    holdet
    0.46
    popd
    0.45
    cerely
    0.45
    ForeignKey
    0.45
    Act Density 0.488%

    No Known Activations