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

    Neuronpedia

    INDEX
    Explanations

    multilingual words and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sensibilité
    0.88
     sensations
    0.82
    ಲ್ಲು
    0.78
    贅
    0.77
     poch
    0.76
     Tôi
    0.75
     vong
    0.75
     beve
    0.74
     bonnes
    0.74
     sada
    0.73
    POSITIVE LOGITS
    ্তির
    0.89
     መጠን
    0.84
    тировать
    0.81
    𝗔
    0.80
    र्थिक
    0.79
    ᄏ
    0.79
    ington
    0.79
    这就是
    0.79
    ты
    0.77
     pomoći
    0.74
    Act Density 0.000%

    No Known Activations