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

    Neuronpedia

    INDEX
    Explanations

    examples/instances

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals containing decimal points.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    >We
    -0.07
     hope
    -0.07
     XCTestCase
    -0.07
    ham
    -0.06
    .GetHashCode
    -0.06
    .ToolTip
    -0.06
     cohort
    -0.06
     SENSOR
    -0.06
     fore
    -0.06
    	ff
    -0.06
    POSITIVE LOGITS
    她的
    0.07
     سبب
    0.07
    مة
    0.06
     دانش
    0.06
    очные
    0.06
    تف
    0.06
    Incorrect
    0.06
     nebylo
    0.06
    一些
    0.06
    /oauth
    0.06
    Act Density 0.065%

    No Known Activations