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

    Neuronpedia

    INDEX
    Explanations

    collections and highlights within various contexts

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

    collection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.44
     createState
    -0.42
     Autónoma
    -0.39
    UserScript
    -0.38
     nettsted
    -0.38
    DeleteMapping
    -0.36
     periódico
    -0.35
    UpInside
    -0.35
     démocratie
    -0.34
    Active
    -0.34
    POSITIVE LOGITS
     collection
    1.03
     collections
    0.97
     Collection
    0.85
     Collections
    0.80
    collection
    0.79
     COLLECTION
    0.77
    collections
    0.72
    COLLECTION
    0.72
    Collection
    0.70
    コレクション
    0.65
    Act Density 0.033%

    No Known Activations