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

    Neuronpedia

    INDEX
    Explanations

    democratic, progressive, socialist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conservative
    0.88
     ಬಿಜೆಪಿ
    0.83
    Conservative
    0.82
     conservatives
    0.77
    保守
    0.76
     బీజేపీ
    0.75
     conservatism
    0.74
    conservative
    0.74
     বিজে
    0.73
     konserv
    0.73
    POSITIVE LOGITS
     Democratic
    1.30
     leftist
    1.19
     Democrats
    1.14
    Democratic
    1.12
     progressive
    1.04
     Democrat
    1.04
     izquier
    1.02
     Left
    1.02
     socialist
    1.00
     left
    0.99
    Act Density 0.052%

    No Known Activations