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

    Neuronpedia

    INDEX
    Explanations

    derivative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forecasts
    -0.08
     delivery
    -0.08
     seeds
    -0.07
    bar
    -0.07
     index
    -0.07
     benchmarks
    -0.07
    Bar
    -0.07
     socialist
    -0.07
    ター
    -0.07
     targets
    -0.07
    POSITIVE LOGITS
     사고
    0.09
     רע
    0.08
    .Listener
    0.08
     נוספים
    0.08
     мегӯ
    0.08
     कैम
    0.08
     намай
    0.08
     მეც
    0.08
    湖
    0.08
     นาที
    0.08
    Act Density 0.013%

    No Known Activations