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

    Neuronpedia

    INDEX
    Explanations

    word then associated word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ھ
    0.43
     Ashe
    0.42
    ্ধ
    0.41
    Y
    0.40
    titled
    0.40
    યુ
    0.40
     Hua
    0.40
    chten
    0.39
     Noida
    0.39
    тические
    0.39
    POSITIVE LOGITS
    ாதார
    0.47
    ைகளுக்கு
    0.45
    钓
    0.45
     Regarding
    0.44
     corrupción
    0.44
     sporad
    0.44
    <unused69>
    0.44
     சேவை
    0.44
    轻
    0.43
     favour
    0.43
    Act Density 0.009%

    No Known Activations