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

    Neuronpedia

    INDEX
    Explanations

    colonization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Каж
    -0.08
     Abstract
    -0.08
     Это
    -0.07
     الأخ
    -0.07
     Сдел
    -0.07
     Можно
    -0.07
     Стар
    -0.07
     Alias
    -0.07
     Precision
    -0.07
    ätä
    -0.07
    POSITIVE LOGITS
     interventions
    0.10
     trouxe
    0.09
    luetooth
    0.09
     chegada
    0.09
    ’arrivée
    0.09
     outsiders
    0.09
     geli
    0.09
    'arrivée
    0.09
     introducing
    0.09
     introdu
    0.09
    Act Density 0.017%

    No Known Activations