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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of a “sleepover” scenario—that is, words like having, sleep, over, together in the context of people spending the night.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rick
    -0.07
     نفت
    -0.07
     Rick
    -0.06
     Results
    -0.06
     �
    -0.06
     Cause
    -0.06
    ds
    -0.06
     minimize
    -0.06
    ากร
    -0.06
    vell
    -0.06
    POSITIVE LOGITS
     использ
    0.07
     }*/↵
    0.07
    .appspot
    0.07
    啊啊
    0.06
    status
    0.06
    _Checked
    0.06
     lawy
    0.06
    ра�
    0.06
    =time
    0.06
     phúc
    0.06
    Act Density 0.126%

    No Known Activations