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

    Neuronpedia

    INDEX
    Explanations

    asking for more about a topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    及び
    0.45
    及
    0.43
    および
    0.42
    了两
    0.41
     andRow
    0.41
    まず
    0.40
     bowiem
    0.40
    ’-
    0.39
     এবং
    0.39
     indistinct
    0.39
    POSITIVE LOGITS
     किंवा
    0.44
    isiin
    0.42
     veya
    0.41
     rohkem
    0.41
    或其他
    0.41
    その他の
    0.40
     ataupun
    0.40
    OR
    0.40
     কিংবা
    0.40
     หรือ
    0.39
    Act Density 0.038%

    No Known Activations