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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    저
    0.50
    GoogleApiClient
    0.49
    راہیم
    0.49
    שים
    0.48
    वता
    0.47
    per
    0.46
    യ
    0.45
    לים
    0.45
    며
    0.44
    족
    0.44
    POSITIVE LOGITS
     مباشرة
    0.47
     информация
    0.46
     అని
    0.45
     exemplo
    0.45
     работа
    0.44
     получа
    0.44
     الجهاز
    0.44
    čko
    0.43
     khăn
    0.43
     Agua
    0.43
    Act Density 0.002%

    No Known Activations