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

    Neuronpedia

    INDEX
    Explanations

    program execution and command-line arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bridal
    0.42
     Gibbs
    0.39
     Bij
    0.38
     Hagg
    0.37
     curved
    0.37
     Peterson
    0.37
     Reef
    0.36
     Golf
    0.36
    تمي
    0.36
     Lee
    0.35
    POSITIVE LOGITS
    ArgumentParser
    0.60
    命令行
    0.58
    Stdin
    0.57
     프로그램
    0.52
    PROGRAM
    0.50
     실행
    0.50
    Stdout
    0.50
    プログラム
    0.49
     პროგრამ
    0.49
     프로그램을
    0.48
    Act Density 0.173%

    No Known Activations