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

    Neuronpedia

    INDEX
    Explanations

    both words (plural)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =========
    0.80
    III
    0.77
     reu
    0.73
    बीसी
    0.71
     cheapest
    0.71
     വിവിധ
    0.71
    കു
    0.70
     dragState
    0.69
     অব
    0.69
    淏
    0.68
    POSITIVE LOGITS
     இருவரும்
    0.96
    ./
    0.95
     Kedua
    0.94
     دو
    0.91
     kedua
    0.91
     دونوں
    0.90
    eduanya
    0.89
     दोनों
    0.89
    兩
    0.88
     ambas
    0.86
    Act Density 0.097%

    No Known Activations