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

    Neuronpedia

    INDEX
    Explanations

    Patents

    np_max-act · gemini-2.0-flash

    The neuron detects tokens that are part of patent citations (e.g. “U.S. Pat. No.” and the numeric identifiers that follow).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     month
    -0.07
    ONSE
    -0.07
     Vaccine
    -0.07
    -month
    -0.06
     prescriptions
    -0.06
     menus
    -0.06
    .units
    -0.06
     occurrence
    -0.06
    /Linux
    -0.06
    iances
    -0.06
    POSITIVE LOGITS
     açık
    0.07
    ！”↵↵
    0.06
    人物
    0.06
     consc
    0.06
     Bethlehem
    0.06
     Especially
    0.06
    okt
    0.06
     muster
    0.06
     heyec
    0.06
    leveland
    0.06
    Act Density 0.008%

    No Known Activations