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

    Neuronpedia

    INDEX
    Explanations

    welcome and freely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conseguiu
    0.83
     غ
    0.76
     удалось
    0.75
     berhasil
    0.75
     gigante
    0.72
     pourriez
    0.71
     Dzięki
    0.70
    guien
    0.70
     بت
    0.70
    具备
    0.68
    POSITIVE LOGITS
     welcome
    1.39
     Welcome
    1.20
    Welcome
    1.11
    welcome
    1.08
     freely
    1.03
    歡迎
    1.00
     welcomes
    0.99
    欢迎
    0.99
     welcomed
    0.98
     स्वागत
    0.98
    Act Density 0.323%

    No Known Activations