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

    Neuronpedia

    INDEX
    Explanations

    please or thank you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thisobject
    0.44
     장면
    0.42
     pulverized
    0.40
    ！
    0.39
     epigenetic
    0.39
     zenith
    0.39
     bildet
    0.38
     description
    0.38
     roadmap
    0.38
     payoff
    0.38
    POSITIVE LOGITS
     किंवा
    0.55
    謝謝
    0.55
     Obrigado
    0.55
    谢谢
    0.54
     अन्यथा
    0.54
     спасибо
    0.53
     Semoga
    0.53
     please
    0.52
     Спасибо
    0.52
     veya
    0.51
    Act Density 0.208%

    No Known Activations