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

    Neuronpedia

    INDEX
    Explanations

    Circuit

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the word “Circuit” in courtroom headings, i.e. references to a Court of Appeals circuit.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    尚
    -0.07
     سبب
    -0.07
    医学
    -0.07
    (_('
    -0.06
     прояв
    -0.06
    нез
    -0.06
     그래
    -0.06
     primaryStage
    -0.06
     ^{[
    -0.06
     李
    -0.06
    POSITIVE LOGITS
     Restoration
    0.07
     diving
    0.07
    /resources
    0.07
    IVE
    0.07
     reminders
    0.07
    ाई
    0.07
    -point
    0.07
     lifetime
    0.06
    Channel
    0.06
    ając
    0.06
    Act Density 0.002%

    No Known Activations