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

    Neuronpedia

    INDEX
    Explanations

    Times

    np_max-act · gemini-2.0-flash

    The neuron detects numeric schedule details—times, dates, days/week, or other temporal numerals in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    azzo
    -0.07
    _tag
    -0.07
     acciones
    -0.06
     fruity
    -0.06
     нуж
    -0.06
     přih
    -0.06
    _IRQHandler
    -0.06
    PointerType
    -0.06
    -bed
    -0.06
    _PUSHDATA
    -0.06
    POSITIVE LOGITS
    Guess
    0.08
     dates
    0.07
    Working
    0.07
    .no
    0.07
     امن
    0.06
     nationalists
    0.06
     courage
    0.06
    Stretch
    0.06
    !!)↵
    0.06
    .controllers
    0.06
    Act Density 0.013%

    No Known Activations