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

    Neuronpedia

    INDEX
    Explanations

    need for something

    np_max-act · gemini-2.0-flash

    The neuron fires for numeric tokens—especially decimal numbers and measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Watts
    -0.07
    SnackBar
    -0.06
     militar
    -0.06
     heads
    -0.06
     markets
    -0.06
     Би
    -0.06
    "F
    -0.06
     saga
    -0.06
     charter
    -0.06
     Henry
    -0.06
    POSITIVE LOGITS
     asoci
    0.07
    сті
    0.07
     condo
    0.06
    :'',↵
    0.06
     先
    0.06
     versatile
    0.06
    imest
    0.06
     Spot
    0.06
    doctor
    0.06
    spot
    0.06
    Act Density 0.073%

    No Known Activations