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

    Neuronpedia

    INDEX
    Explanations

    Gear

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “gear.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    UDENT
    -0.07
     Uncle
    -0.07
    uni
    -0.07
     uncle
    -0.07
     Solomon
    -0.07
     Palm
    -0.07
    ArgumentException
    -0.06
    又
    -0.06
     대학
    -0.06
     Wu
    -0.06
    POSITIVE LOGITS
     gear
    0.16
     Gear
    0.13
     gears
    0.12
    Gear
    0.12
     geared
    0.09
    ear
    0.08
    gear
    0.08
     gearing
    0.07
     ra
    0.07
     gearbox
    0.07
    Act Density 0.005%

    No Known Activations