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

    Neuronpedia

    INDEX
    Explanations

    "Hello, World!"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    സ്ലാ
    0.89
     బాల
    0.86
     invariably
    0.82
    侓
    0.81
    范
    0.80
     balcon
    0.80
    סי
    0.79
     theseKeys
    0.79
     ناول
    0.79
    umbai
    0.79
    POSITIVE LOGITS
    </h2>
    0.72
     Before
    0.64
    .
    0.62
    ."
    0.60
     Tradition
    0.60
    ":
    0.60
    ".
    0.59
    }}{(
    0.59
    用意
    0.58
     Spl
    0.57
    Act Density 0.291%

    No Known Activations