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

    Neuronpedia

    INDEX
    Explanations

    awards and recognition

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric tokens or numerical expressions (quantities, dates, codes, measurements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    please
    -0.08
     //@
    -0.07
     conquest
    -0.07
     sequel
    -0.07
    ListOf
    -0.07
     McM
    -0.07
    '>"+
    -0.06
    िथ
    -0.06
    cedures
    -0.06
     پاس
    -0.06
    POSITIVE LOGITS
    igrate
    0.07
    xo
    0.06
     زیبا
    0.06
     theoretically
    0.05
     영향을
    0.05
    議
    0.05
     rebuild
    0.05
    law
    0.05
    (Keys
    0.05
     ayuda
    0.05
    Act Density 0.006%

    No Known Activations