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

    Neuronpedia

    INDEX
    Explanations

    Positive advancements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尊
    -0.07
     Fathers
    -0.06
    Wat
    -0.06
     warehouse
    -0.06
     fourteen
    -0.06
     окра
    -0.06
     Uma
    -0.06
     облич
    -0.06
    ех
    -0.06
     데
    -0.06
    POSITIVE LOGITS
    現在
    0.07
     Jacket
    0.07
     Mash
    0.06
           ↵↵
    0.06
     Greenwood
    0.06
    蛇
    0.06
    .ComponentModel
    0.06
    [l
    0.06
     Checkbox
    0.06
     креп
    0.06
    Act Density 0.068%

    No Known Activations