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

    Neuronpedia

    INDEX
    Explanations

    in the moment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نیاز
    0.74
     Plattform
    0.69
     contenu
    0.67
    似的
    0.67
    intero
    0.67
    ankind
    0.66
     объекта
    0.65
     ہوئی
    0.64
     mahdoll
    0.64
     عدد
    0.64
    POSITIVE LOGITS
     midst
    2.10
     meantime
    1.78
     vicinity
    1.72
     وفي
    1.54
     context
    1.51
     guise
    1.34
     absence
    1.27
     wake
    1.21
    context
    1.21
     realm
    1.19
    Act Density 0.380%

    No Known Activations