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

    Neuronpedia

    INDEX
    Explanations

    list item definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.49
    3
    0.47
    िंग
    0.45
     to
    0.43
    लट
    0.43
     With
    0.43
     Conclusion
    0.42
     In
    0.42
     briefing
    0.42
    4
    0.42
    POSITIVE LOGITS
    ،
    0.52
    ՝
    0.49
    0.47
    ۔
    0.44
    ٬
    0.44
    ，
    0.43
    ၊
    0.43
     ،
    0.42
     ওরফে
    0.42
    াবেক
    0.41
    Act Density 0.061%

    No Known Activations