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

    Neuronpedia

    INDEX
    Explanations

    code definition syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    បន្ថ
    0.43
     dürfte
    0.41
    DEBUGFS
    0.39
     magari
    0.38
    ∑</
    0.38
    漂
    0.37
    ＮＡＮＡ
    0.37
     मिळू
    0.37
     mile
    0.36
    ลด
    0.36
    POSITIVE LOGITS
     syntax
    1.00
    语法
    0.99
    Syntax
    0.95
     Syntax
    0.95
    syntax
    0.87
     declaration
    0.76
     keyword
    0.72
     sint
    0.72
     synt
    0.71
     Declaration
    0.69
    Act Density 0.076%

    No Known Activations