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

    Neuronpedia

    INDEX
    Explanations

    Announcements/Promotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    retry
    -0.09
     filenames
    -0.09
     memes
    -0.08
    .Cart
    -0.08
     mutate
    -0.08
     mutation
    -0.08
     boyfriend
    -0.07
     mutated
    -0.07
     saisons
    -0.07
     Gloss
    -0.07
    POSITIVE LOGITS
     참석
    0.18
     సమావేశ
    0.17
     seminars
    0.17
     অনুষ্ঠিত
    0.17
    会议
    0.16
     ಸಭ
    0.16
     workshops
    0.16
    開催
    0.16
     attendees
    0.16
     बैठक
    0.15
    Act Density 0.313%

    No Known Activations