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

    Neuronpedia

    INDEX
    Explanations

    control and surveillance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鯊
    0.42
    BufOffset
    0.40
    경상
    0.40
     weathered
    0.39
     साहस
    0.39
    splitter
    0.39
    ሽ
    0.39
     rocked
    0.38
    irregular
    0.38
     rock
    0.38
    POSITIVE LOGITS
     authoritarian
    0.85
     surveillance
    0.83
     totalitarian
    0.81
     coercive
    0.77
     Surveillance
    0.77
     control
    0.76
     controlling
    0.75
    control
    0.75
    控制
    0.75
     контроль
    0.71
    Act Density 0.429%

    No Known Activations