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

    Neuronpedia

    INDEX
    Explanations

    offers, discount, flexibility, True

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    参考文献
    0.46
     dint
    0.43
     etc
    0.42
    ↵
    0.42
     D
    0.42
    nig
    0.41
     index
    0.41
     query
    0.41
     rmse
    0.41
     smeared
    0.41
    POSITIVE LOGITS
     предлагает
    0.55
     предлага
    0.52
     brings
    0.51
     poveć
    0.49
     nonprofit
    0.49
     Announces
    0.47
     homebuyers
    0.47
    ൻ
    0.47
    的价格
    0.46
    Weekly
    0.46
    Act Density 0.002%

    No Known Activations