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

    Neuronpedia

    INDEX
    Explanations

    Repository

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不仅可以
    -0.08
    [array
    -0.07
     bức
    -0.07
     EDGE
    -0.07
    新年
    -0.07
     sortie
    -0.07
     elt
    -0.07
     QT
    -0.07
     vaz
    -0.07
    杞
    -0.07
    POSITIVE LOGITS
    瘕
    0.07
    噬
    0.07
    톈
    0.07
    sının
    0.06
    	resolve
    0.06
    медицин
    0.06
     ECB
    0.06
    改进
    0.06
     reputed
    0.06
     Мак
    0.06
    Act Density 0.003%

    No Known Activations