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

    Neuronpedia

    INDEX
    Explanations

    constant

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of defining or using “constants.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     WANT
    -0.06
    score
    -0.06
    Aff
    -0.06
     많
    -0.06
     Patty
    -0.06
     конкур
    -0.06
     squat
    -0.06
     결혼
    -0.06
    	Intent
    -0.06
     ATT
    -0.06
    POSITIVE LOGITS
    Ads
    0.08
     gentlemen
    0.07
     constants
    0.07
    usted
    0.07
    .DE
    0.06
     YA
    0.06
    sten
    0.06
    earn
    0.06
     basın
    0.06
    ophysical
    0.06
    Act Density 0.015%

    No Known Activations