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

    Neuronpedia

    INDEX
    Explanations

    customer support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    科学家
    0.55
     dissection
    0.55
     scientific
    0.53
     scientists
    0.53
     scientist
    0.52
     Scientists
    0.50
    scientists
    0.48
     collaborations
    0.47
    錐
    0.47
     Scientist
    0.44
    POSITIVE LOGITS
    Customer
    0.91
     Customer
    0.82
    customer
    0.77
     customer
    0.76
    客服
    0.75
    Customers
    0.73
     Customers
    0.71
    customers
    0.70
     customers
    0.66
     ग्राहकों
    0.65
    Act Density 0.403%

    No Known Activations