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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     us
    -0.07
    نت
    -0.07
    苷
    -0.06
    開發
    -0.06
    Cpp
    -0.06
    ("%
    -0.06
     esp
    -0.06
    んだ
    -0.06
     hated
    -0.06
    された
    -0.06
    POSITIVE LOGITS
    imited
    0.07
     stacked
    0.07
    楼层
    0.07
    	order
    0.07
     directing
    0.07
    boundary
    0.07
    废旧
    0.07
    .cards
    0.07
     lear
    0.07
    樨
    0.06
    Act Density 0.002%

    No Known Activations