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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash

    This neuron fires on expressions of duration or longevity (e.g. “for years to come”).

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

    descriptions of items that highlight their aesthetic and functional qualities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    虎
    -0.07
    jobs
    -0.07
    sharing
    -0.07
    icha
    -0.07
    )throws
    -0.07
     Mosque
    -0.07
    =false
    -0.07
    High
    -0.07
    کی
    -0.06
     subpo
    -0.06
    POSITIVE LOGITS
     Banner
    0.07
     dlouh
    0.07
     Chapters
    0.07
     ejercicio
    0.07
     być
    0.07
     cope
    0.06
     enviado
    0.06
    XB
    0.06
     تض
    0.06
     Word
    0.06
    Act Density 0.018%

    No Known Activations