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

    Neuronpedia

    INDEX
    Explanations

    large numbers and scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    门
    0.47
     Form
    0.46
     Door
    0.46
     Clinic
    0.45
     Service
    0.45
     Holi
    0.45
     जले
    0.45
     Oper
    0.44
     strutt
    0.43
     door
    0.43
    POSITIVE LOGITS
     trillions
    1.15
     billions
    1.10
     trillion
    0.90
     milliards
    0.88
     gigantic
    0.88
     millions
    0.86
     billionaire
    0.84
    billion
    0.84
     gigantes
    0.84
     miliardi
    0.82
    Act Density 0.168%

    No Known Activations