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

    Neuronpedia

    INDEX
    Explanations

    roles and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     presidency
    0.49
     ministries
    0.48
     lords
    0.47
     선생님
    0.47
     Ministries
    0.46
     priestly
    0.46
     queens
    0.46
    Teachers
    0.46
     Teachers
    0.45
     Someone
    0.45
    POSITIVE LOGITS
     Assistant
    0.92
     Acting
    0.90
     Deputy
    0.84
    Assistant
    0.77
    Acting
    0.74
    Outgoing
    0.72
     Associate
    0.72
     outgoing
    0.70
    Deputy
    0.69
     Interim
    0.65
    Act Density 0.010%

    No Known Activations