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

    Neuronpedia

    INDEX
    Explanations

    expressing certainty or doubt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.76
    EST
    0.69
    ፣
    0.59
     EUROPE
    0.58
    ，
    0.57
     sabia
    0.55
    ên
    0.55
     ESA
    0.54
     impor
    0.54
     Evalu
    0.54
    POSITIVE LOGITS
    ably
    0.83
    પણે
    0.72
    в
    0.68
    ্স
    0.65
    ą
    0.64
     что
    0.63
    во
    0.63
    eine
    0.62
    这不是
    0.61
     रुप
    0.60
    Act Density 2.677%

    No Known Activations