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

    Neuronpedia

    INDEX
    Explanations

    difference between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಣೆ
    1.02
     sebagainya
    1.00
    ري
    0.96
    ът
    0.93
    ﻴ
    0.92
    뿜
    0.92
    له
    0.91
    به
    0.89
    semantics
    0.89
    ക്ഷ
    0.86
    POSITIVE LOGITS
    laştır
    0.98
    。
    0.95
     Augusta
    0.93
    。\
    0.92
    㫴
    0.91
    هما
    0.90
     pard
    0.89
    право
    0.88
    。)
    0.85
     Kait
    0.84
    Act Density 0.231%

    No Known Activations