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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पद्ध
    0.45
    ointments
    0.42
    لاج
    0.41
    酒店
    0.40
     hotel
    0.39
    製作
    0.39
    صرية
    0.39
     पद्धति
    0.38
    ˢ
    0.38
     চক্ষ
    0.37
    POSITIVE LOGITS
    Syntax
    1.48
     syntax
    1.47
     Syntax
    1.45
     parser
    1.36
     parse
    1.33
     parsing
    1.30
    语法
    1.30
     AST
    1.27
     grammar
    1.27
    syntax
    1.27
    Act Density 0.072%

    No Known Activations