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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Keyword
    -0.06
    月
    -0.06
    messages
    -0.06
     propulsion
    -0.06
    Db
    -0.06
    (amount
    -0.06
     transc
    -0.06
     друг
    -0.06
     john
    -0.06
    Books
    -0.06
    POSITIVE LOGITS
    classCallCheck
    0.07
    leitung
    0.06
    .ComponentResourceManager
    0.06
    橋
    0.06
    untas
    0.06
    avel
    0.06
     parcels
    0.06
    {!!
    0.06
     rains
    0.06
     ninh
    0.06
    Act Density 0.009%

    No Known Activations