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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SuspendLayout
    -0.73
     kasarigan
    -0.69
    CodeAttribute
    -0.66
    endpush
    -0.64
     estekak
    -0.60
    getSystemService
    -0.59
    ManagedBean
    -0.58
    RenderAtEndOf
    -0.58
     propOrder
    -0.58
    sidemargin
    -0.56
    POSITIVE LOGITS
     to
    0.67
     it
    0.62
     preferring
    0.58
     realizing
    0.57
     realising
    0.55
     discours
    0.54
     preparing
    0.54
     favoring
    0.54
     discussing
    0.54
     الاطلاع
    0.54
    Act Density 0.072%

    No Known Activations