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

    Neuronpedia

    INDEX
    Explanations

    density, stars, world, patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.54
    9
    0.50
     microfiber
    0.48
    1
    0.45
    imbing
    0.45
    2
    0.44
    doesn
    0.43
     behaviors
    0.43
    katore
    0.42
    ្សែ
    0.41
    POSITIVE LOGITS
     दें
    0.54
     याद
    0.49
     గుర్త
    0.48
    鿆
    0.47
     जहां
    0.47
    秀
    0.46
     Ahora
    0.45
    恶
    0.45
     दि
    0.45
     అది
    0.45
    Act Density 0.010%

    No Known Activations