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

    Neuronpedia

    INDEX
    Explanations

    Health and performance

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of one’s ability to function or perform (e.g. “function effectively,” “easier to fall asleep”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     setTitle
    -0.07
     menus
    -0.06
    ectors
    -0.06
    Pie
    -0.06
    CriticalSection
    -0.06
    ürn
    -0.06
    KG
    -0.06
    _windows
    -0.06
    инг
    -0.06
     Melissa
    -0.06
    POSITIVE LOGITS
    _eof
    0.07
     franç
    0.07
     SingleChildScrollView
    0.06
    �
    0.06
     fossils
    0.06
    .ImageLayout
    0.06
    describe
    0.06
     didnt
    0.06
    ..
    0.06
     Aberdeen
    0.06
    Act Density 0.034%

    No Known Activations