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

    Neuronpedia

    INDEX
    Explanations

    uf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATCH
    -0.08
    Liverpool
    -0.07
     kino
    -0.07
    경영
    -0.07
     }:
    -0.07
     resp
    -0.07
    獬
    -0.06
     datas
    -0.06
     sparked
    -0.06
    	printk
    -0.06
    POSITIVE LOGITS
    CESS
    0.07
    肢
    0.07
    のこと
    0.07
    め
    0.07
    usband
    0.06
    ブル
    0.06
    低
    0.06
     Sle
    0.06
    鬟
    0.06
    讳
    0.06
    Act Density 0.001%

    No Known Activations