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

    Neuronpedia

    INDEX
    Explanations

    code and data handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rooms
    0.67
    गंज
    0.63
     Prospects
    0.60
    arlane
    0.59
    ურად
    0.58
     Battista
    0.58
     Opportunities
    0.58
     Eg
    0.57
    ារ
    0.57
    Room
    0.57
    POSITIVE LOGITS
     д
    0.84
     drains
    0.82
     BAG
    0.79
     bag
    0.78
    하나
    0.78
     handbag
    0.75
     রাজার
    0.75
    誇
    0.74
     দৃঢ়
    0.74
     desafio
    0.73
    Act Density 0.002%

    No Known Activations