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

    Neuronpedia

    INDEX
    Explanations

    Something arriving soon

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect personal identifying information—tokens indicating names, street addresses, and other numeric contact/location details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    situations involving emergencies and medical crises.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     assemblies
    -0.07
     Discovery
    -0.07
     notified
    -0.06
    ريس
    -0.06
     дает
    -0.06
     spar
    -0.06
    กรณ
    -0.06
     shorten
    -0.06
     interns
    -0.06
     threaded
    -0.06
    POSITIVE LOGITS
     chocolate
    0.07
    ugo
    0.06
    }','
    0.06
     leds
    0.06
     %%
    0.06
    /an
    0.06
    0.06
    -fin
    0.06
     towering
    0.06
     pageTitle
    0.06
    Act Density 0.142%

    No Known Activations