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

    Neuronpedia

    INDEX
    Explanations

    Supreme Court

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Judge
    0.78
     Judge
    0.75
     judge
    0.71
    Supp
    0.69
    judge
    0.69
     supplemental
    0.66
    supp
    0.65
     Supp
    0.64
    supplement
    0.64
     juez
    0.64
    POSITIVE LOGITS
     Supreme
    1.32
    Supreme
    1.25
     supreme
    1.07
     सुप्रीम
    1.02
    supreme
    1.01
    最高
    0.98
     सर्वोच्च
    0.91
     최고
    0.87
     höchste
    0.80
     最高
    0.79
    Act Density 0.005%

    No Known Activations