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

    Neuronpedia

    INDEX
    Explanations

    tax planning and compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.84
    は
    0.82
    ियों
    0.80
     threaded
    0.80
    ী
    0.80
    ку
    0.79
     букмекерлер
    0.78
     upholstered
    0.77
    는
    0.76
     thatched
    0.75
    POSITIVE LOGITS
    ↵↵
    1.05
     Tax
    1.04
    Tax
    0.91
     as
    0.90
    as
    0.84
    o
    0.82
    λ
    0.80
     TAX
    0.80
    be
    0.79
    n
    0.78
    Act Density 0.009%

    No Known Activations