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

    Neuronpedia

    INDEX
    Explanations

    combining concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WPF
    0.39
     zapewn
    0.37
     цель
    0.37
    idla
    0.37
     той
    0.36
    attin
    0.36
     प्रयास
    0.36
     размещения
    0.36
     цифро
    0.36
    噪
    0.36
    POSITIVE LOGITS
     militari
    0.39
     intégré
    0.37
    刑事
    0.36
     democracy
    0.35
     mortgages
    0.35
     shakespeare
    0.35
     hamburgers
    0.35
     political
    0.34
     sentenced
    0.34
    Mann
    0.34
    Act Density 0.353%

    No Known Activations