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

    Neuronpedia

    INDEX
    Explanations

    indented

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ever
    -0.61
     trajets
    -0.60
    MIDDLEWARE
    -0.60
     shade
    -0.59
     recevez
    -0.58
    odb
    -0.57
     AspNetCore
    -0.57
    StoryboardSegue
    -0.56
     requestCode
    -0.56
    ized
    -0.56
    POSITIVE LOGITS
    s
    0.85
    y
    0.77
    ImageContext
    0.58
    kumar
    0.57
    t
    0.57
    ی
    0.56
    saved
    0.55
    BuilderFactory
    0.49
    subpackage
    0.48
    ádza
    0.47
    Act Density 0.057%

    No Known Activations