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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron activates on references to time spans, especially duration words like “years.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rockets
    -0.07
     اپ
    -0.06
    _life
    -0.06
    。她
    -0.06
     JsonConvert
    -0.06
    _entries
    -0.06
     Juice
    -0.06
     Kes
    -0.06
     ordinances
    -0.06
     Known
    -0.06
    POSITIVE LOGITS
     ακό
    0.06
     Abbott
    0.06
     Rough
    0.06
     chăm
    0.06
     理
    0.06
     перед
    0.06
    べき
    0.06
     진행
    0.06
    ophobic
    0.06
     pořád
    0.06
    Act Density 0.075%

    No Known Activations