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

    Neuronpedia

    INDEX
    Explanations

    affirming LGBTQ+ rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nurse
    0.54
     Probleme
    0.52
     problemi
    0.49
     problèmes
    0.47
     Severe
    0.46
     melancholy
    0.45
    课堂
    0.45
     worrisome
    0.44
    严重的
    0.44
    皞
    0.44
    POSITIVE LOGITS
     revenue
    0.65
     capitalist
    0.60
    revenue
    0.55
     income
    0.55
     royalties
    0.55
     सालाना
    0.55
     capitalists
    0.54
     taxes
    0.54
     revenues
    0.53
     monetize
    0.53
    Act Density 0.003%

    No Known Activations