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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash

    The neuron fires on temporal expressions denoting years or specific time periods (e.g. dates, “academic year,” “fiscal year,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    メージ
    -0.07
    Fred
    -0.07
     Pett
    -0.07
     ol
    -0.06
     Kral
    -0.06
     Russians
    -0.06
    Lee
    -0.06
     ní
    -0.06
     крас
    -0.06
    653
    -0.06
    POSITIVE LOGITS
     revision
    0.07
     тиж
    0.07
    ُوا
    0.06
     самов
    0.06
    ']?></
    0.06
     ๆ
    0.06
    _^(
    0.06
    _OVERFLOW
    0.06
    ?}",
    0.06
    _CHOICES
    0.06
    Act Density 0.018%

    No Known Activations