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

    Neuronpedia

    INDEX
    Explanations

    final answer boxed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.25
     服务
    0.25
    服务
    0.24
    ঘর
    0.24
     Score
    0.24
     toDo
    0.23
     ότι
    0.23
    सीना
    0.23
     Amts
    0.23
     it
    0.22
    POSITIVE LOGITS
     variant
    0.22
     quartet
    0.22
     classically
    0.22
     classical
    0.22
     elated
    0.22
    EN
    0.22
    まとめ
    0.21
     revisited
    0.21
    arXiv
    0.21
    講演
    0.21
    Act Density 0.048%

    No Known Activations