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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens (e.g., numbers, timestamps, and decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     chọn
    -0.07
    dda
    -0.07
     میدان
    -0.06
    ۱۵
    -0.06
     Ý
    -0.06
     استخدام
    -0.06
     Logged
    -0.06
     безопасности
    -0.06
     서울
    -0.06
    尖
    -0.06
    POSITIVE LOGITS
    /************************
    0.06
    <style
    0.06
    _PACKET
    0.06
    .disabled
    0.06
    <uint
    0.06
    lexical
    0.06
    (dispatch
    0.06
    iculos
    0.06
     Sağ
    0.06
     Markets
    0.05
    Act Density 0.161%

    No Known Activations