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

    Neuronpedia

    INDEX
    Explanations

    questions and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vestidos
    0.42
     සු
    0.42
    덫
    0.41
    ধানা
    0.41
    গ্রহায়ণ
    0.39
    ोरेशन
    0.39
     veter
    0.39
     maksimal
    0.38
     heroism
    0.38
     servidores
    0.38
    POSITIVE LOGITS
     பய
    0.43
     கேள்
    0.41
    ファイ
    0.41
     منت
    0.40
     вопросов
    0.40
     प्रश्नों
    0.39
    ﺌ
    0.38
    かも
    0.37
    ォ
    0.37
     вопросы
    0.36
    Act Density 0.000%

    No Known Activations