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

    Neuronpedia

    INDEX
    Explanations

    political and social economics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GOP
    0.63
     Republican
    0.63
    Republican
    0.61
     Republicans
    0.55
     republican
    0.54
     బీజేపీ
    0.52
     político
    0.49
     政
    0.47
     बीजेपी
    0.47
     ಬಿಜೆಪಿ
    0.47
    POSITIVE LOGITS
     Bernie
    0.55
    Bern
    0.55
     Bern
    0.47
     Bernard
    0.46
    Bernard
    0.46
     Sander
    0.42
     Binary
    0.41
     Bernoulli
    0.41
     Bloomberg
    0.40
     blanch
    0.39
    Act Density 0.010%

    No Known Activations