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

    Neuronpedia

    INDEX
    Explanations

    except Exception as e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parámetro
    0.81
    ούς
    0.77
    ınd
    0.74
    লো
    0.74
    niv
    0.74
    "><
    0.73
    ffin
    0.73
    TestData
    0.72
    ேய
    0.72
    een
    0.71
    POSITIVE LOGITS
     whatever
    0.90
    ங்கள்
    0.88
     शशि
    0.83
     oneness
    0.82
     Turtles
    0.81
     اس
    0.80
     Kimura
    0.79
     que
    0.78
     follic
    0.78
    whatever
    0.78
    Act Density 0.026%

    No Known Activations