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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens—especially version numbers and issue or ticket IDs embedded in URLs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    uxtap
    -0.06
     fracture
    -0.06
     defendant
    -0.06
     silhouette
    -0.06
    .Make
    -0.06
     lavish
    -0.06
    Seat
    -0.06
     سخ
    -0.06
    Offers
    -0.06
     ngọt
    -0.05
    POSITIVE LOGITS
    -da
    0.07
    اضي
    0.06
     art
    0.06
     Donald
    0.06
    ằ
    0.06
     ’
    0.06
    appl
    0.06
     Latter
    0.06
     даль
    0.06
    Hola
    0.06
    Act Density 0.002%

    No Known Activations