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

    Neuronpedia

    INDEX
    Explanations

    countries and geography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    0.83
     lined
    0.80
    ak
    0.80
    ம்
    0.79
     conjugation
    0.79
    록
    0.78
    ଣ
    0.78
    রা
    0.77
    ての
    0.76
    0.75
    POSITIVE LOGITS
    anse
    1.16
    wide
    1.15
    ీయ
    1.10
    esque
    1.06
    longest
    1.04
    funk
    0.95
    ESE
    0.93
    peu
    0.90
    frica
    0.90
    tall
    0.90
    Act Density 0.236%

    No Known Activations