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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to numerical expressions—especially decimal numbers, percentages, and other statistical figures—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     foreigners
    -0.06
     spoken
    -0.06
    ль
    -0.06
     grenade
    -0.06
     chairs
    -0.06
     XV
    -0.06
     patiently
    -0.06
     crossing
    -0.05
    emie
    -0.05
     futbol
    -0.05
    POSITIVE LOGITS
    autoload
    0.07
    #,
    0.07
    dbContext
    0.07
    練
    0.07
    _MODULE
    0.07
     workload
    0.06
    .slice
    0.06
    =settings
    0.06
    .setOutput
    0.06
    STS
    0.06
    Act Density 0.026%

    No Known Activations