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

    Neuronpedia

    INDEX
    Explanations

    please let me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yeah
    0.51
     yep
    0.44
    yeah
    0.42
     smack
    0.40
     sometimes
    0.39
     neurons
    0.39
     Вообще
    0.39
     probs
    0.39
    Yeah
    0.38
     reflexes
    0.38
    POSITIVE LOGITS
     Please
    0.93
    please
    0.91
     please
    0.91
    Please
    0.85
     PLEASE
    0.85
    请
    0.83
    請
    0.83
     пожалуйста
    0.77
     कृपया
    0.76
     请
    0.75
    Act Density 0.005%

    No Known Activations