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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .aspect
    -0.07
    ão
    -0.07
    Assistant
    -0.06
    赋
    -0.06
     Investing
    -0.06
     artık
    -0.06
    他知道
    -0.06
     insisting
    -0.06
     edição
    -0.06
     actually
    -0.06
    POSITIVE LOGITS
     Rolex
    0.08
     SERIAL
    0.08
    OV
    0.07
    🆖
    0.07
    	job
    0.07
    dataProvider
    0.07
     discounted
    0.07
    (movie
    0.07
     manufactured
    0.06
     privat
    0.06
    Act Density 0.001%

    No Known Activations