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

    Neuronpedia

    INDEX
    Explanations

    toilets bathrooms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saham
    0.56
     MSCI
    0.56
     MeV
    0.55
     Optimization
    0.54
     XML
    0.54
     GeV
    0.52
     Rays
    0.52
     Cortex
    0.51
     Kagan
    0.51
     epistem
    0.51
    POSITIVE LOGITS
     toilet
    3.84
     toilets
    3.67
    Toilet
    3.52
     bathroom
    3.42
    toilet
    3.39
     restroom
    3.39
     Toilet
    3.33
     bathrooms
    3.27
     restrooms
    3.22
    bathroom
    3.03
    Act Density 0.103%

    No Known Activations