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

    Neuronpedia

    INDEX
    Explanations

    first-person perspective and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     você
    0.58
    しましょう
    0.57
     youll
    0.53
    你可以
    0.52
    咱們
    0.50
    you
    0.49
     Você
    0.49
     voidaan
    0.48
     ourselves
    0.48
     ours
    0.48
    POSITIVE LOGITS
     ನನಗೆ
    0.88
     எனக்கு
    0.82
    对我
    0.79
     mujhe
    0.78
     నాకు
    0.77
    Мне
    0.74
     мне
    0.74
    让我
    0.73
    我现在
    0.73
    讓我
    0.71
    Act Density 0.019%

    No Known Activations