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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron activates on repeated occurrences of the word “same.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     moduleId
    -0.07
     Shipping
    -0.06
     втра
    -0.06
     Hire
    -0.06
     Such
    -0.06
     KR
    -0.06
    -testid
    -0.06
    creen
    -0.06
     useDispatch
    -0.06
    уляр
    -0.06
    POSITIVE LOGITS
     axle
    0.07
    cp
    0.06
    uč
    0.06
    ग
    0.06
    θρώ
    0.06
    ován
    0.06
     простран
    0.06
     بم
    0.06
    islav
    0.06
    _defaults
    0.06
    Act Density 0.006%

    No Known Activations