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

    Neuronpedia

    INDEX
    Explanations

    reporting and improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emergency
    0.47
    acetamol
    0.46
     griseo
    0.44
     victim
    0.40
     EMERGENCY
    0.40
     Emergency
    0.39
     आयुर्वेदिक
    0.39
     binoculars
    0.39
     പോലീസ്
    0.39
     detectors
    0.39
    POSITIVE LOGITS
     개선
    0.55
     действие
    0.50
    反馈
    0.48
     memperbaiki
    0.48
     improvements
    0.47
     Feedback
    0.47
    Improvements
    0.46
    改进
    0.45
     изменений
    0.45
    改善
    0.45
    Act Density 0.048%

    No Known Activations