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

    Neuronpedia

    INDEX
    Explanations

    discounts on purchases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     riveting
    -0.08
     scrib
    -0.08
     Scratch
    -0.08
    Pid
    -0.08
     cosy
    -0.07
    scrib
    -0.07
     Tear
    -0.07
     ktoś
    -0.07
     captivating
    -0.07
     Train
    -0.07
    POSITIVE LOGITS
     товаров
    0.11
    Eligible
    0.11
     taxable
    0.10
     eligible
    0.10
     purchases
    0.10
     товары
    0.10
     کالا
    0.10
    _discount
    0.09
     Eligible
    0.09
     taxes
    0.09
    Act Density 0.013%

    No Known Activations