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

    Neuronpedia

    INDEX
    Explanations

    importance and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PopupWindow
    0.44
     ছেড়ে
    0.42
     """"
    0.39
     کی
    0.38
    淤
    0.38
     স্যা
    0.37
     """
    0.37
     खी
    0.37
     농
    0.37
     overflowing
    0.37
    POSITIVE LOGITS
     PERSONAL
    0.49
    principles
    0.49
    𐰚
    0.48
     erwartet
    0.48
    حان
    0.47
     gehalten
    0.47
     sensibil
    0.46
     SINGLE
    0.46
    Principles
    0.46
     önemlidir
    0.46
    Act Density 0.027%

    No Known Activations