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

    Neuronpedia

    INDEX
    Explanations

    on fraud detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Employees
    0.67
     speichern
    0.65
     ኩ
    0.65
     employees
    0.65
     funcionários
    0.63
    Employees
    0.63
    urses
    0.63
    eyeglasses
    0.63
     Departments
    0.63
    送信
    0.62
    POSITIVE LOGITS
     risk
    0.81
     Risk
    0.74
    risk
    0.72
     advising
    0.72
    Risk
    0.69
     strategy
    0.64
     gap
    0.63
     Gap
    0.63
     forecasting
    0.62
     stakeholder
    0.62
    Act Density 0.531%

    No Known Activations