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

    Neuronpedia

    INDEX
    Explanations

    entertainment category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.16
    os
    0.92
    on
    0.87
    as
    0.84
    ö
    0.84
    ü
    0.83
    There
    0.82
    ，
    0.82
    N
    0.81
    As
    0.77
    POSITIVE LOGITS
     leisure
    0.89
     recreation
    0.88
     recreational
    0.81
    taining
    0.80
     amused
    0.80
    \}
    0.72
    মূলক
    0.71
     speculated
    0.70
    休闲
    0.70
     பொழுது
    0.69
    Act Density 0.006%

    No Known Activations