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

    Neuronpedia

    INDEX
    Explanations

    ope

    np_max-act · gemini-2.0-flash

    The neuron is a named‐entity detector, firing on capitalized organization, brand, and product names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     yrs
    -0.07
    Ы
    -0.06
    vlan
    -0.06
    ugador
    -0.06
    artists
    -0.06
    yasal
    -0.06
    �
    -0.06
    pag
    -0.06
    ेखन
    -0.06
    'ın
    -0.06
    POSITIVE LOGITS
     INTER
    0.06
    .Engine
    0.06
    esco
    0.06
     Rogue
    0.06
                     ↵
    0.06
     \\↵
    0.06
     [*
    0.06
    /cmd
    0.06
                               ↵
    0.06
    calendar
    0.06
    Act Density 0.274%

    No Known Activations