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

    Neuronpedia

    INDEX
    Explanations

    history and empires

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially years, centuries, and other number references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    IMENT
    -0.07
    -service
    -0.07
     TH
    -0.07
    _jobs
    -0.06
    hua
    -0.06
    italize
    -0.06
     miracles
    -0.06
     fined
    -0.06
    159
    -0.06
    <Card
    -0.06
    POSITIVE LOGITS
     �
    0.07
    external
    0.07
     Ibid
    0.07
    _about
    0.07
    ixer
    0.07
    bite
    0.06
    subtitle
    0.06
     Obr
    0.06
    gear
    0.06
     зако
    0.06
    Act Density 0.031%

    No Known Activations