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

    Neuronpedia

    INDEX
    Explanations

    Toy Story

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gende
    -0.07
    ди
    -0.07
    曛
    -0.07
    تنظ
    -0.07
    униципальн
    -0.07
    AREN
    -0.07
    :view
    -0.07
    *n
    -0.06
    EG
    -0.06
    底气
    -0.06
    POSITIVE LOGITS
     Lives
    0.07
    Creators
    0.07
    遍及
    0.07
    成果转化
    0.07
     alkal
    0.06
     genitals
    0.06
    Aus
    0.06
    ﹹ
    0.06
    账
    0.06
    .plus
    0.06
    Act Density 0.083%

    No Known Activations