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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens (especially decimal numbers) in the source.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     PhoneNumber
    -0.07
     pract
    -0.06
    Sy
    -0.06
    Navigate
    -0.06
     fragment
    -0.06
    Summary
    -0.06
    terminate
    -0.06
    روب
    -0.06
     reader
    -0.06
     smelling
    -0.06
    POSITIVE LOGITS
    """↵↵↵
    0.07
     المدر
    0.07
    ，现在
    0.07
    ческий
    0.06
    `
↵
    0.06
     грав
    0.06
     Chloe
    0.06
    """),↵
    0.06
    ？”
    0.06
     лица
    0.06
    Act Density 0.004%

    No Known Activations