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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ;;
    -0.07
     Fiction
    -0.06
    cih
    -0.06
    Specifications
    -0.06
    ahr
    -0.06
    '#
    -0.06
     polynomial
    -0.06
    .bed
    -0.06
    閉
    -0.06
    cnt
    -0.06
    POSITIVE LOGITS
     příspě
    0.07
     truyền
    0.07
    _repeat
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    .Enabled
    0.06
     AB
    0.06
    引用
    0.06
     encyclopedia
    0.06
     Terrorism
    0.06
    μή
    0.06
    Act Density 0.054%

    No Known Activations