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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash

    This neuron responds to explicit acknowledgments of comprehension or compliance (e.g., “understand”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Peaks
    -0.07
     Wells
    -0.06
     kval
    -0.06
    rı
    -0.06
     Sight
    -0.06
     usa
    -0.06
    pictures
    -0.06
     elf
    -0.06
    VES
    -0.06
     Sanctuary
    -0.06
    POSITIVE LOGITS
     Burlington
    0.07
    <\/
    0.07
    :maj
    0.07
    _term
    0.07
     overshadow
    0.06
     understood
    0.06
    には
    0.06
     entend
    0.06
     Burk
    0.06
    จ
    0.06
    Act Density 0.014%

    No Known Activations