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

    Neuronpedia

    INDEX
    Explanations

    latin-1 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻗ
    0.40
     desliz
    0.40
    லிய
    0.39
     Guthrie
    0.39
     söyled
    0.39
    闿
    0.38
    귤
    0.38
    ከላከ
    0.38
     Rutland
    0.38
    ரா
    0.37
    POSITIVE LOGITS
     Latin
    0.88
    Latin
    0.86
     LAT
    0.75
     latin
    0.71
    Lat
    0.70
     lat
    0.69
     Lat
    0.68
    LAT
    0.68
    lat
    0.67
    latin
    0.66
    Act Density 0.003%

    No Known Activations