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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act · gemini-2.0-flash

    This neuron activates specifically on numeric tokens (digits or numbers) within sequence-prediction contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Six
    -0.07
    another
    -0.07
    Louis
    -0.06
     jackets
    -0.06
     //
↵
    -0.06
     biggest
    -0.06
    -0.06
    -0.06
     taped
    -0.06
    -0.06
    POSITIVE LOGITS
     didSet
    0.06
     Ao
    0.06
    .WriteByte
    0.06
     компон
    0.06
     Telegram
    0.06
     entsprech
    0.06
     Value
    0.06
     Howell
    0.06
    حاد
    0.06
    мон
    0.06
    Act Density 0.001%

    No Known Activations