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

    Neuronpedia

    INDEX
    Explanations

    result

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens, especially years and other numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     испыт
    -0.07
     ARM
    -0.06
     warm
    -0.06
    '],↵
    -0.06
     CONTACT
    -0.06
    olated
    -0.06
    硬
    -0.06
    Bind
    -0.06
     awe
    -0.06
     peanut
    -0.06
    POSITIVE LOGITS
    -pt
    0.07
    Writable
    0.07
     така
    0.06
     vùng
    0.06
     JsonRequestBehavior
    0.06
    ικοί
    0.06
    .at
    0.06
    はない
    0.06
     Timeline
    0.06
     dejar
    0.06
    Act Density 0.527%

    No Known Activations