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

    Neuronpedia

    INDEX
    Explanations

    number of bedrooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    你
    0.82
     you
    0.75
    0
    0.75
    いた
    0.75
    しまう
    0.71
    どう
    0.70
    ॓
    0.69
    おそらく
    0.68
     it
    0.67
    ありません
    0.67
    POSITIVE LOGITS
     bedroom
    1.19
     bedrooms
    1.13
     Bedroom
    1.00
    ↵
    0.98
     Bedrooms
    0.91
    bedroom
    0.89
    ting
    0.88
    bedrooms
    0.82
    卧室
    0.80
    test
    0.79
    Act Density 0.001%

    No Known Activations