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

    Neuronpedia

    INDEX
    Explanations

    news on politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தாவர
    0.47
     Ouvrard
    0.45
    协会
    0.45
    砻
    0.43
     څرنګوالی
    0.43
     доли
    0.42
     анима
    0.42
     県
    0.41
    赣
    0.41
    溽
    0.41
    POSITIVE LOGITS
     MSNBC
    0.60
     politically
    0.52
     political
    0.50
    CNN
    0.48
    political
    0.47
     AMERICA
    0.47
    istani
    0.46
     analyst
    0.46
     राजनीतिक
    0.45
     Washington
    0.44
    Act Density 0.012%

    No Known Activations