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

    Neuronpedia

    INDEX
    Explanations

    contextual continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     concentrated
    0.51
     중요한
    0.45
     참여
    0.43
     shaped
    0.41
     centered
    0.41
     във
    0.41
     conjugacy
    0.41
     कितनी
    0.40
     accès
    0.40
     sentence
    0.40
    POSITIVE LOGITS
    p
    0.68
    د
    0.57
    t
    0.56
    يمي
    0.53
    دي
    0.51
    ينات
    0.51
    n
    0.51
    k
    0.51
    اد
    0.50
    kül
    0.50
    Act Density 0.010%

    No Known Activations