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

    Neuronpedia

    INDEX
    Explanations

    shrines

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ky
    0.55
     சித்த
    0.55
     착
    0.55
     mesure
    0.54
     chan
    0.54
     windows
    0.53
     الصفحه
    0.53
     ಅನುಪ
    0.53
    麩
    0.52
     Windows
    0.52
    POSITIVE LOGITS
    ⛩
    0.74
    神社
    0.70
     enshrined
    0.69
     shrine
    0.66
     shrines
    0.65
     Shrine
    0.64
    軻
    0.63
     worshipped
    0.61
    瓊
    0.61
    Shr
    0.59
    Act Density 0.006%

    No Known Activations