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

    Neuronpedia

    INDEX
    Explanations

    vendor

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “vendor” (and its variants like “vendors,” “Vendor Spotlight,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    lüğü
    -0.08
     Braves
    -0.08
    uraa
    -0.07
     heartbeat
    -0.07
     Life
    -0.07
     حفظ
    -0.07
     flashes
    -0.07
    १�
    -0.07
     přičemž
    -0.07
     seals
    -0.07
    POSITIVE LOGITS
     vendor
    0.11
     vendors
    0.10
    vendor
    0.10
    .vendor
    0.09
    /vendor
    0.09
     Vendor
    0.09
    Vendor
    0.08
     Vand
    0.08
    enor
    0.08
     vending
    0.08
    Act Density 0.003%

    No Known Activations