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

    Neuronpedia

    INDEX
    Explanations

    changes, updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    έργ
    -0.08
    würdigkeiten
    -0.07
     жит
    -0.07
    чын
    -0.07
    ინ
    -0.07
     прож
    -0.07
     жизн
    -0.07
    imachinery
    -0.07
    iness
    -0.07
    станавли
    -0.07
    POSITIVE LOGITS
     أصبح
    0.13
     أصبحت
    0.13
     recentemente
    0.12
     geändert
    0.12
     recently
    0.11
    以来
    0.11
    変更
    0.11
     changed
    0.11
     Changed
    0.11
     recientemente
    0.11
    Act Density 0.163%

    No Known Activations