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

    Neuronpedia

    INDEX
    Explanations

    10

    np_max-act · gemini-2.0-flash

    The neuron fires on the list‐position numbers (e.g. the “10,” “5,” “2,” etc.) used to mark items in “Top N” style lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    addWidget
    -0.07
    ,System
    -0.07
    	pt
    -0.06
    Pred
    -0.06
     Aut
    -0.06
     dando
    -0.06
     new
    -0.06
    ，存于
    -0.06
     Cul
    -0.06
    サービス
    -0.06
    POSITIVE LOGITS
    0.07
    -scal
    0.06
     countdown
    0.06
     Ranking
    0.06
    (double
    0.06
    reesome
    0.06
     seven
    0.06
    crets
    0.06
    EventArgs
    0.06
    ские
    0.06
    Act Density 0.007%

    No Known Activations