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

    Neuronpedia

    INDEX
    Explanations

    Article snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     steak
    -0.90
    kenes
    -0.78
     Steak
    -0.76
    Steak
    -0.50
     <>",
    -0.47
     bParam
    -0.46
     høy
    -0.45
    =[]
    -0.41
    steak
    -0.40
    WaitGroup
    -0.39
    POSITIVE LOGITS
     Walkover
    0.76
     متعلقه
    0.76
     وتسجيلات
    0.72
     AssemblyTitle
    0.71
     للمعارف
    0.70
     المعرف
    0.69
    MemoryWarning
    0.68
    complexContent
    0.67
    ⓧ
    0.66
    room
    0.65
    Act Density 0.020%

    No Known Activations