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

    Neuronpedia

    INDEX
    Explanations

    article text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extensively
    -0.07
    оры
    -0.07
    -worker
    -0.06
     smuggling
    -0.06
    Finance
    -0.06
     cracking
    -0.06
    -workers
    -0.06
    وير
    -0.06
     shade
    -0.06
     raining
    -0.06
    POSITIVE LOGITS
     verbosity
    0.08
     культуры
    0.07
    atório
    0.07
     nedenle
    0.06
    кування
    0.06
     авт
    0.06
    Tipo
    0.06
     Visibility
    0.06
    .ReadOnly
    0.06
     Discounts
    0.06
    Act Density 0.075%

    No Known Activations