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

    Neuronpedia

    INDEX
    Explanations

    code lines and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     структура
    0.41
     উদ্দেশ্যে
    0.39
     estrutura
    0.39
    strukt
    0.39
     водо
    0.38
    pyrid
    0.38
     परिवेश
    0.38
     estructura
    0.38
     구조
    0.38
    pump
    0.37
    POSITIVE LOGITS
    语句
    1.16
     statement
    1.13
     statements
    1.08
    statement
    0.99
    Statement
    0.96
     line
    0.96
     Statement
    0.93
     Statements
    0.93
    Statements
    0.91
    statements
    0.90
    Act Density 0.041%

    No Known Activations