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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the publication or release of works, particularly in academic or literary contexts

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

    books and literary works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.53
    PreferredItem
    -0.45
    BagConstraints
    -0.45
    Jeografia
    -0.44
    новништво
    -0.43
    ModelAdmin
    -0.43
    GEBURTS
    -0.41
     sécurité
    -0.41
    הערות
    -0.41
     seguridad
    -0.40
    POSITIVE LOGITS
     creator
    0.49
     literary
    0.47
     publications
    0.47
     publishing
    0.47
    literary
    0.47
     published
    0.46
     titles
    0.45
     books
    0.45
     littéraire
    0.44
    Literary
    0.44
    Act Density 0.044%

    No Known Activations