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

    Neuronpedia

    INDEX
    Explanations

    Wuxia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Neural
    -0.10
     Productivity
    -0.09
     Sampling
    -0.09
    Sampling
    -0.08
     productivity
    -0.08
    Os
    -0.08
     Annex
    -0.08
    _sampling
    -0.08
     Os
    -0.08
     landfill
    -0.08
    POSITIVE LOGITS
    秘籍
    0.12
    侠
    0.10
     forged
    0.10
     allegiance
    0.09
    争霸
    0.09
    Forg
    0.09
     rivalry
    0.08
     equips
    0.08
     किं
    0.08
    天下
    0.08
    Act Density 0.006%

    No Known Activations