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

    Neuronpedia

    INDEX
    Explanations

    billion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    捂
    -0.08
    拐
    -0.07
    (sim
    -0.07
    iffany
    -0.07
     Cu
    -0.07
     Moms
    -0.07
     caves
    -0.07
    _Sh
    -0.07
     Dtype
    -0.07
     إذ
    -0.07
    POSITIVE LOGITS
    這個
    0.07
     Estates
    0.07
     전체
    0.07
     third
    0.07
    南宁市
    0.07
    もの
    0.06
    (init
    0.06
    lington
    0.06
    医疗服务
    0.06
     nguồn
    0.06
    Act Density 0.009%

    No Known Activations