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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric expressions (numbers with units or currency), such as fees, prices, dimensions, weights, or percentages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cores
    -0.07
     encompass
    -0.07
    ública
    -0.06
    quest
    -0.06
     CPC
    -0.06
    nees
    -0.06
     prejud
    -0.06
    liğinin
    -0.06
     Winning
    -0.06
    isable
    -0.06
    POSITIVE LOGITS
     почина
    0.07
    ㅋㅋㅋㅋ
    0.07
     жизнь
    0.07
    蛇
    0.06
    .sc
    0.06
     Broker
    0.06
    .GetType
    0.06
     StatusCode
    0.06
    』↵↵
    0.06
    =!
    0.06
    Act Density 0.023%

    No Known Activations