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

    Neuronpedia

    INDEX
    Explanations

    time: **

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تي
    0.50
    دت
    0.48
    كيف
    0.48
     Grower
    0.47
    िक
    0.47
    a
    0.47
    ل
    0.46
    ফ
    0.46
     অ্যাল
    0.46
    o
    0.45
    POSITIVE LOGITS
     שה
    0.45
    도
    0.42
     미국
    0.41
     직접
    0.41
     토
    0.41
     เน
    0.40
    Sciences
    0.40
     กรณี
    0.40
    ORG
    0.39
     에
    0.38
    Act Density 0.036%

    No Known Activations