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

    Neuronpedia

    INDEX
    Explanations

    fraudulent activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    体验
    0.85
     актуа
    0.85
     experiential
    0.84
     loneliness
    0.83
     pessim
    0.83
     möchte
    0.82
    苦手
    0.81
    Neuro
    0.80
     Lonely
    0.80
    體驗
    0.79
    POSITIVE LOGITS
     fraudulent
    1.89
     fraudulently
    1.83
     collusion
    1.68
     smuggled
    1.60
     fraud
    1.58
     alleged
    1.58
     embezz
    1.54
     smuggling
    1.52
     embezzlement
    1.51
     allegations
    1.50
    Act Density 0.316%

    No Known Activations