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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     duquel
    -0.61
    — 
    -0.60
    didSet
    -0.57
    CppMethod
    -0.55
     podjela
    -0.55
    .*")]
    -0.54
    numbered
    -0.53
    GeneratedCode
    -0.53
     NUKAT
    -0.53
    abetes
    -0.53
    POSITIVE LOGITS
     تضيفلها
    0.57
     المعيارى
    0.56
    enumi
    0.56
     poveznice
    0.50
     Chwiliwch
    0.49
    roma
    0.47
    f
    0.45
     appeals
    0.45
    ConverterFactory
    0.44
    OuterClass
    0.44
    Act Density 0.006%

    No Known Activations