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

    Neuronpedia

    INDEX
    Explanations

    customer loyalty programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ệu
    0.44
    iminary
    0.44
     prü
    0.43
    作文
    0.42
     scientifiques
    0.41
     út
    0.40
    ྦ
    0.40
    டுவத
    0.40
     Lancet
    0.40
    酘
    0.39
    POSITIVE LOGITS
     loyalty
    1.21
     Loyalty
    1.16
     loyal
    0.97
     Customer
    0.95
    Loy
    0.94
     Loyal
    0.91
     customer
    0.89
    Customer
    0.84
    customer
    0.82
     customers
    0.81
    Act Density 0.084%

    No Known Activations