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

    Neuronpedia

    INDEX
    Explanations

    Past tense "be"

    np_max-act · gemini-2.0-flash

    The neuron identifies date or time expressions—particularly years, ordinals (e.g. “5 th”), and related tokens in event‐date phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ReturnType
    -0.06
     Dup
    -0.06
     та
    -0.06
     وسی
    -0.06
    <dim
    -0.06
     REGISTER
    -0.06
    endar
    -0.06
     Nếu
    -0.06
     Euler
    -0.06
     ה
    -0.06
    POSITIVE LOGITS
     attracted
    0.07
     Мы
    0.06
    side
    0.06
    crc
    0.06
     annihil
    0.06
    _mk
    0.06
     menggunakan
    0.06
     üret
    0.06
    .labelControl
    0.06
     recruiters
    0.06
    Act Density 0.019%

    No Known Activations