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

    Neuronpedia

    INDEX
    Explanations

    RA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    る
    -0.07
     Truck
    -0.07
     بايد
    -0.07
     starred
    -0.07
     Flower
    -0.06
    имер
    -0.06
    rier
    -0.06
     Dirt
    -0.06
     Merge
    -0.06
    μεν
    -0.06
    POSITIVE LOGITS
     RA
    0.06
     OA
    0.06
    ra
    0.06
    -da
    0.06
     ESA
    0.06
     保
    0.06
    ){
↵
    0.06
     attributable
    0.06
     CActive
    0.06
     Vaughan
    0.06
    Act Density 0.001%

    No Known Activations