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

    Neuronpedia

    INDEX
    Explanations

    biographies and death dates

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens—especially dates, years, and other number values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sf
    -0.07
    asis
    -0.07
    婷
    -0.06
     Flush
    -0.06
    Pokud
    -0.06
    .za
    -0.06
     lần
    -0.06
     skepticism
    -0.06
     tard
    -0.06
    tolua
    -0.06
    POSITIVE LOGITS
    運動
    0.07
     debating
    0.07
    quality
    0.06
    _series
    0.06
     acet
    0.06
     Hamm
    0.06
    _UT
    0.06
     عملية
    0.06
     structured
    0.06
    ZE
    0.06
    Act Density 0.014%

    No Known Activations