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

    Neuronpedia

    INDEX
    Explanations

    talk to your doctor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     чыныгы
    0.54
     공식
    0.48
     직접
    0.46
     मनोविज्ञान
    0.46
    <footer>
    0.45
     आधिकारिक
    0.45
     պ
    0.44
     तृतीय
    0.44
     официально
    0.44
     실제
    0.43
    POSITIVE LOGITS
     doctor
    0.87
     physician
    0.70
     pharmacist
    0.68
    doctor
    0.68
     Doctor
    0.67
     doctors
    0.65
     dokter
    0.64
    医生
    0.63
    醫生
    0.63
    Doctor
    0.61
    Act Density 0.004%

    No Known Activations