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

    Neuronpedia

    INDEX
    Explanations

    itarian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ஒன்று
    -0.08
     α
    -0.08
     المحلية
    -0.08
     त्यांनी
    -0.07
    冷热
    -0.07
     насел
    -0.07
    ైవ
    -0.07
     INTERNET
    -0.07
     spars
    -0.07
    沪
    -0.07
    POSITIVE LOGITS
     Judges
    0.09
    너
    0.09
     flexible
    0.08
     rewards
    0.08
     soucis
    0.08
     Rewards
    0.08
     destruction
    0.08
    Flexible
    0.08
     Flexible
    0.08
     upbringing
    0.08
    Act Density 0.001%

    No Known Activations