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

    Neuronpedia

    INDEX
    Explanations

    multilingual text fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     playGame
    0.43
     gameOver
    0.41
     OpenCV
    0.39
     humanoid
    0.39
    转载
    0.38
    শেষে
    0.38
     phổ
    0.38
     doit
    0.37
    也要
    0.37
     deven
    0.35
    POSITIVE LOGITS
    rição
    0.42
    Nord
    0.42
    amek
    0.40
    '=>'','
    0.40
    अय
    0.40
    Brun
    0.39
    جات
    0.38
    кий
    0.38
     ль
    0.38
    ADES
    0.38
    Act Density 0.146%

    No Known Activations