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

    Neuronpedia

    INDEX
    Explanations

    Indian names and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    பிலோ
    0.58
     Milo
    0.50
    ீரல்
    0.46
    เบียน
    0.46
    Cogn
    0.45
    சில்
    0.44
    ర్రీ
    0.44
    Glen
    0.43
    unbox
    0.43
     Tanger
    0.42
    POSITIVE LOGITS
    appa
    1.13
    ayya
    1.02
    amma
    1.01
    APPA
    0.93
    anna
    0.86
    iah
    0.86
    appan
    0.80
    aiya
    0.80
    app
    0.78
    aih
    0.76
    Act Density 0.002%

    No Known Activations