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

    Neuronpedia

    INDEX
    Explanations

    Gal followed by various word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elje
    0.43
    hints
    0.41
    こんな
    0.40
    這樣
    0.39
    however
    0.39
    ダメージ
    0.39
     Terbang
    0.39
     पद्ध
    0.39
    മല
    0.39
    埝
    0.38
    POSITIVE LOGITS
     gal
    0.99
     GAL
    0.89
     Gal
    0.86
    Gal
    0.76
    gal
    0.69
     galactose
    0.68
     Gall
    0.66
     gall
    0.66
     Gala
    0.64
     gala
    0.63
    Act Density 0.008%

    No Known Activations