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

    Neuronpedia

    INDEX
    Explanations

    environment variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    メガ
    0.41
     floribus
    0.40
    ဴ
    0.39
     Гали
    0.39
    BlackElo
    0.38
    োগ্য
    0.38
    bitro
    0.37
     supon
    0.37
    喁
    0.36
     datap
    0.36
    POSITIVE LOGITS
    环境变量
    1.67
     environmental
    1.48
     environment
    1.44
    環境
    1.42
     환경
    1.42
    的环境
    1.40
     環境
    1.38
     env
    1.36
     पर्यावरण
    1.36
    Environment
    1.35
    Act Density 0.022%

    No Known Activations