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

    Neuronpedia

    INDEX
    Explanations

    initiates flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    环境保护
    0.44
     جمه
    0.44
    ijuana
    0.40
    诊断
    0.39
     Honduras
    0.38
    কাতার
    0.38
    定义的
    0.37
    ئات
    0.37
     환경
    0.36
    笤
    0.36
    POSITIVE LOGITS
     kara
    0.41
     sinon
    0.41
    ori
    0.38
     sino
    0.38
     cin
    0.38
     главное
    0.38
     arquivo
    0.37
     предметы
    0.37
     students
    0.37
    ‌ന
    0.37
    Act Density 0.000%

    No Known Activations