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

    Neuronpedia

    INDEX
    Explanations

    bathrooms and restrooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     t
    1.02
                    
    1.01
                   
    0.91
     Многие
    0.91
    ist
    0.91
     \
    0.90
     l
    0.88
    0
    0.84
     sigh
    0.83
    OS
    0.82
    POSITIVE LOGITS
     toilet
    1.41
    🚽
    1.41
    🛁
    1.40
     urin
    1.38
    Toilet
    1.34
    toilet
    1.30
     excret
    1.30
     Toilet
    1.30
    тт
    1.26
     bathroom
    1.25
    Act Density 0.023%

    No Known Activations