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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numerical or quantitative expressions—numbers, measurements, and statistics—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     traveler
    -0.06
     万
    -0.06
     sequelize
    -0.06
     устанавлива
    -0.06
     Lal
    -0.06
     stringBuffer
    -0.06
     присутств
    -0.06
     Shine
    -0.06
    .Line
    -0.06
     因
    -0.06
    POSITIVE LOGITS
    елів
    0.07
    .Controllers
    0.07
    北京
    0.06
     Lunar
    0.06
    선거
    0.06
     suc
    0.06
    .Div
    0.06
    τύ
    0.06
     når
    0.06
    IsEmpty
    0.06
    Act Density 0.464%

    No Known Activations