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

    Neuronpedia

    INDEX
    Explanations

    references to documents and documentation

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

    mentions of document

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     épar
    -0.54
     pitié
    -0.53
     élar
    -0.52
     popularidad
    -0.52
    lewati
    -0.52
     ennemi
    -0.50
     préfé
    -0.49
     zasi
    -0.49
     empezar
    -0.48
     direta
    -0.48
    POSITIVE LOGITS
     Document
    1.18
     document
    1.13
    Document
    1.03
    document
    1.01
     documents
    0.96
     Documents
    0.92
     DOCUMENT
    0.86
    ocument
    0.82
    getDocument
    0.82
    DOCUMENT
    0.82
    Act Density 0.017%

    No Known Activations