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

    Neuronpedia

    INDEX
    Explanations

    not just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     것을
    0.75
     मुताब
    0.72
    राबाद
    0.69
    চিতে
    0.68
    Mve
    0.68
    ించాలి
    0.66
    됩
    0.66
     స్థాప
    0.65
    esterly
    0.65
     गाइ
    0.62
    POSITIVE LOGITS
     just
    4.04
    just
    3.55
     simply
    3.48
     Just
    3.45
    Just
    3.43
     merely
    2.99
     JUST
    2.97
    simply
    2.92
     Simply
    2.89
     simplemente
    2.87
    Act Density 1.435%

    No Known Activations