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

    Neuronpedia

    INDEX
    Explanations

    World Series championship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    巫
    -0.71
     sending
    -0.69
    劾
    -0.68
    chufe
    -0.67
    AHL
    -0.67
    관
    -0.67
    stig
    -0.66
     overall
    -0.65
    鱗
    -0.65
    学会
    -0.65
    POSITIVE LOGITS
     World
    2.89
    World
    2.50
     Series
    2.36
    Series
    2.13
     WORLD
    1.75
    WORLD
    1.73
     WS
    1.71
    ワールド
    1.70
    world
    1.66
    series
    1.62
    Act Density 0.031%

    No Known Activations