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

    Neuronpedia

    INDEX
    Explanations

    requests for information or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gotta
    0.99
     echte
    0.92
    だから
    0.91
    kids
    0.88
    ちゃんと
    0.88
     kids
    0.87
     faktisk
    0.86
     ด่า
    0.86
     진짜
    0.84
    しかも
    0.83
    POSITIVE LOGITS
     please
    1.25
    Kindly
    1.15
     Kindly
    1.14
    请
    1.11
     kindly
    1.11
    Please
    1.08
    please
    1.05
     Please
    1.05
     कृपया
    1.04
     advise
    1.01
    Act Density 0.317%

    No Known Activations