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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash

    The neuron activates on warranty mentions—especially numeric “X-year warranty” phrases.

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

    specific product features and details related to design and compatibility.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    002
    -0.07
    flu
    -0.07
    human
    -0.06
    \common
    -0.06
    (ConfigurationManager
    -0.06
     chơi
    -0.06
     arter
    -0.06
     Empty
    -0.06
     Saudi
    -0.06
    는지
    -0.06
    POSITIVE LOGITS
     gec
    0.07
     أو
    0.06
    .program
    0.06
    :left
    0.06
     departure
    0.06
     кількість
    0.06
    ρκεια
    0.06
     condemning
    0.06
    大學
    0.06
     아이
    0.06
    Act Density 0.004%

    No Known Activations