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

    Neuronpedia

    INDEX
    Explanations

    operational disturbance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Пла
    0.44
    슴
    0.42
    ளும்
    0.41
    シリ
    0.41
    पट
    0.40
    isei
    0.39
    ipients
    0.39
     нуле
    0.38
    ပ်
    0.38
    Бу
    0.38
    POSITIVE LOGITS
    鎖
    0.46
     disturbs
    0.42
     cross
    0.42
     disturb
    0.42
    disturbance
    0.42
     operational
    0.41
     disturbance
    0.41
     cop
    0.40
     disturbed
    0.40
     检测
    0.40
    Act Density 0.000%

    No Known Activations