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

    Neuronpedia

    INDEX
    Explanations

    check it out

    np_max-act · gemini-2.0-flash

    The neuron detects second-person imperative calls to action—phrases like “check it out yourself,” “have a look for yourself,” etc., that urge the reader to try or verify something personally.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    {↵
    -0.07
    kHz
    -0.07
     sociale
    -0.07
    |=↵
    -0.06
     seja
    -0.06
    american
    -0.06
     tuy
    -0.06
    Ly
    -0.06
    great
    -0.06
     mere
    -0.06
    POSITIVE LOGITS
    ('-',
    0.07
     производства
    0.06
     MIN
    0.06
     Badge
    0.06
    important
    0.06
     长
    0.06
     آغاز
    0.06
     एज
    0.06
    alace
    0.06
    кап
    0.06
    Act Density 0.069%

    No Known Activations