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

    Neuronpedia

    INDEX
    Explanations

    technical jargon and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NASA
    0.85
     seorang
    0.79
     Nintendo
    0.77
     Airbnb
    0.76
     YouTube
    0.75
     rejoice
    0.73
     AutoCAD
    0.73
     mengambil
    0.72
     Instagram
    0.71
     hippie
    0.70
    POSITIVE LOGITS
     metrics
    0.93
     interfaces
    0.88
     observables
    0.87
     descriptors
    0.85
     компонентов
    0.83
     components
    0.83
     orifices
    0.83
     operands
    0.82
     hierarchies
    0.82
     correlations
    0.81
    Act Density 0.664%

    No Known Activations