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

    Neuronpedia

    INDEX
    Explanations

    accommodation types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🇭
    0.47
     QApplication
    0.43
     운동
    0.42
    日本の
    0.40
    購買
    0.40
    💅
    0.40
     pilates
    0.40
     substring
    0.39
     Singapore
    0.39
     compras
    0.39
    POSITIVE LOGITS
     cottages
    0.66
     bungalows
    0.62
    Meals
    0.55
     bungal
    0.54
     Meals
    0.53
     meals
    0.52
     lawns
    0.48
     bungalow
    0.47
     Cott
    0.47
     orchard
    0.46
    Act Density 0.001%

    No Known Activations