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

    Neuronpedia

    INDEX
    Explanations

    covered

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric values (especially decimal/floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Regarding
    -0.06
     Jelly
    -0.06
    pair
    -0.06
     Plugins
    -0.06
    Fu
    -0.06
     сах
    -0.06
    İng
    -0.06
    Monitoring
    -0.06
     家
    -0.06
     Кон
    -0.06
    POSITIVE LOGITS
    ใจ
    0.07
     Deg
    0.07
    ивается
    0.06
    (Seq
    0.06
    geh
    0.06
    _text
    0.06
     sustained
    0.06
     industri
    0.06
    egie
    0.06
     asbestos
    0.06
    Act Density 0.241%

    No Known Activations