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

    Neuronpedia

    INDEX
    Explanations

    critique of progressive identity politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hemi
    0.47
     greedy
    0.40
     കിട
    0.40
     Konrad
    0.39
    驛
    0.39
     रॉयल
    0.39
     geom
    0.39
    铤
    0.39
    粨
    0.38
     typhoid
    0.37
    POSITIVE LOGITS
     woke
    1.02
     woken
    0.95
     activism
    0.88
     activist
    0.86
     progressive
    0.85
     activists
    0.80
     PC
    0.72
     identity
    0.71
    progressive
    0.71
     SJ
    0.71
    Act Density 0.031%

    No Known Activations