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

    Neuronpedia

    INDEX
    Explanations

    customer churn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arj
    0.43
     brooding
    0.39
     grasping
    0.37
     Broom
    0.37
    陌
    0.37
    ococcal
    0.36
    ool
    0.36
     possession
    0.36
    Yz
    0.36
    onesome
    0.36
    POSITIVE LOGITS
     dealings
    0.92
     거래
    0.88
    客户
    0.84
     сотрудни
    0.81
     고객
    0.80
    客戶
    0.79
    ลูกค้า
    0.79
     customers
    0.78
    거래
    0.78
     مشتری
    0.77
    Act Density 0.014%

    No Known Activations