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

    Neuronpedia

    INDEX
    Explanations

    sorting/ordering text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     άλλο
    -0.08
     März
    -0.08
    があります
    -0.08
    ισμό
    -0.08
     "";↵
    -0.08
    ρού
    -0.08
     diğer
    -0.08
     quaternion
    -0.08
     Aufent
    -0.07
     Heng
    -0.07
    POSITIVE LOGITS
    .sorted
    0.11
     sorted
    0.11
    _sorted
    0.10
     leaderboard
    0.10
    (sorted
    0.10
    Sorted
    0.10
     rankings
    0.10
     topped
    0.09
    排行榜
    0.09
     Sorted
    0.09
    Act Density 0.013%

    No Known Activations