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

    Neuronpedia

    INDEX
    Explanations

    I am an AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在這裡
    0.80
    <unused260>
    0.77
     someone
    0.74
     something
    0.72
    在这里
    0.72
     సంద
    0.71
     here
    0.70
     taller
    0.70
     здесь
    0.70
     disini
    0.69
    POSITIVE LOGITS
    oda
    0.87
    revenue
    0.76
    opholes
    0.75
    ила
    0.75
    ība
    0.75
     Ensure
    0.74
    debate
    0.74
    undered
    0.73
     संदर्भित
    0.73
    Revenue
    0.72
    Act Density 0.011%

    No Known Activations