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

    Neuronpedia

    INDEX
    Explanations

    bedroom and its context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    1.04
    ()
    0.99
    0
    0.92
    TimeStamp
    0.91
    お待ち
    0.91
    ০০
    0.89
     it
    0.88
    ються
    0.88
     That
    0.87
    Valid
    0.87
    POSITIVE LOGITS
    ни
    1.33
    ↵
    1.09
     bedroom
    1.06
    -
    0.98
     bedrooms
    0.86
    ة
    0.85
    ა
    0.83
    ش
    0.81
     midfielders
    0.80
    نا
    0.79
    Act Density 0.001%

    No Known Activations