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

    Neuronpedia

    INDEX
    Explanations

    python files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    나가
    1.01
    smallskip
    0.98
    Ngoài
    0.98
    Maze
    0.97
     luas
    0.97
    나
    0.96
     Když
    0.96
    GameObject
    0.94
    ي
    0.94
    maze
    0.92
    POSITIVE LOGITS
    speople
    0.98
    z
    0.97
    ses
    0.96
    ون
    0.93
    ises
    0.91
    го
    0.87
    ž
    0.85
    sur
    0.84
     erst
    0.83
    sk
    0.82
    Act Density 0.010%

    No Known Activations