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

    Neuronpedia

    INDEX
    Explanations

    mentions of brand name drugs or products

    oai_token-act-pair · gemini-2.0-flash

    medical or software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.57
    ex
    -0.47
    “
    -0.45
    selt
    -0.43
    シ
    -0.43
     single
    -0.43
     segi
    -0.42
    sh
    -0.42
    Mona
    -0.42
    </em>
    -0.41
    POSITIVE LOGITS
    XmlAccessorType
    0.78
    PyExc
    0.78
     المعيارى
    0.77
     AssemblyProduct
    0.74
     otomatig
    0.73
     vPvB
    0.71
    ddots
    0.69
     Hift
    0.69
     تضيفلها
    0.68
     Jefus
    0.68
    Act Density 0.509%

    No Known Activations