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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    statements about the consistency of summaries with their source documents.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     massages
    -0.07
    (percent
    -0.06
    ss
    -0.06
    ('/')
    -0.06
     memories
    -0.06
     pendant
    -0.06
    不会
    -0.06
    .put
    -0.06
    тою
    -0.06
    categorias
    -0.06
    POSITIVE LOGITS
     адрес
    0.07
     kullanımı
    0.07
     lands
    0.06
    =start
    0.06
     sunshine
    0.06
     pint
    0.06
    ‌شوند
    0.06
     relent
    0.06
     school
    0.06
     newcomer
    0.06
    Act Density 0.000%

    No Known Activations