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

    Neuronpedia

    INDEX
    Explanations

    ID

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arque
    -0.47
    หมือน
    -0.45
    cki
    -0.43
    лиз
    -0.43
     NSObject
    -0.43
    iterranean
    -0.42
    ولی
    -0.42
    ListView
    -0.42
    front
    -0.42
    ไว้
    -0.41
    POSITIVE LOGITS
    +:+
    0.70
    expandindo
    0.64
    roek
    0.59
    ECH
    0.56
     EconPapers
    0.55
     "..\..\..\
    0.55
    رشف
    0.54
    تقاوى
    0.54
    ScopeManager
    0.53
     protoimpl
    0.51
    Act Density 0.002%

    No Known Activations