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

    Neuronpedia

    INDEX
    Explanations

    exceptions, conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     status
    -0.99
     Status
    -0.89
    status
    -0.88
     characterized
    -0.78
    Status
    -0.77
     besides
    -0.77
     STATUS
    -0.71
    n
    -0.68
    STATUS
    -0.65
    uding
    -0.65
    POSITIVE LOGITS
    Бахар
    0.80
    webElementXpaths
    0.75
     GenerationType
    0.73
    AddTagHelper
    0.72
    ьаж
    0.72
    Personendaten
    0.71
     betweenstory
    0.69
     Winaray
    0.69
    ConstraintMaker
    0.69
     NUKAT
    0.68
    Act Density 1.617%

    No Known Activations