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

    Neuronpedia

    INDEX
    Explanations

    measuring time duration

    np_max-act · gemini-2.0-flash

    This neuron detects the “from … to …” constructions that introduce time intervals or procedure durations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     visionary
    -0.07
     ό
    -0.06
     目
    -0.06
     tort
    -0.06
     addressed
    -0.06
     Мак
    -0.06
     Exhibit
    -0.06
     believing
    -0.06
     positively
    -0.06
    _cross
    -0.06
    POSITIVE LOGITS
    liğe
    0.07
    \DB
    0.07
     кров
    0.06
    '};↵
    0.06
    '}}↵
    0.06
    olojik
    0.06
    gregar
    0.06
    یستم
    0.06
     Wag
    0.06
    cin
    0.06
    Act Density 0.049%

    No Known Activations