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

    Neuronpedia

    INDEX
    Explanations

    Your contact information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Employer
    0.53
    employer
    0.50
    僱
    0.50
     employer
    0.49
     नियोक्ता
    0.48
    Occupation
    0.48
     должности
    0.48
     EMPLOY
    0.47
     Employer
    0.46
     occupation
    0.45
    POSITIVE LOGITS
     optimal
    0.38
     intricate
    0.36
     आरामदायक
    0.36
    lyn
    0.35
    лин
    0.35
     cleanly
    0.35
     Addressing
    0.35
     Americans
    0.34
     professional
    0.34
     healthy
    0.34
    Act Density 0.007%

    No Known Activations