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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_max-act · gemini-2.0-flash

    This neuron specifically responds to numerical tokens—especially numeric constants and decimal numbers—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    čan
    -0.07
    措
    -0.07
     Lưu
    -0.07
     klíč
    -0.06
    ValueCollection
    -0.06
     nack
    -0.06
    lerle
    -0.06
     scaleFactor
    -0.06
    andy
    -0.06
     thread
    -0.06
    POSITIVE LOGITS
    .SubItems
    0.07
    ounty
    0.06
    ointments
    0.06
    隐
    0.06
     زمین
    0.06
    aco
    0.06
    .modified
    0.06
     знаю
    0.06
     RESP
    0.06
    withdraw
    0.06
    Act Density 0.005%

    No Known Activations