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

    Neuronpedia

    INDEX
    Explanations

    for i in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有可能
    0.49
     입력
    0.45
     increment
    0.43
     परिवर्तन
    0.43
     education
    0.42
    過程
    0.42
     포
    0.41
     그러나
    0.41
     احتمال
    0.40
     ganglia
    0.40
    POSITIVE LOGITS
    م
    0.51
    м
    0.50
    m
    0.46
    te
    0.44
    <0xA0>
    0.43
    т
    0.42
    यों
    0.42
    i
    0.41
    ت
    0.41
     esposa
    0.40
    Act Density 0.009%

    No Known Activations