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

    Neuronpedia

    INDEX
    Explanations

    references to historical or notable buildings and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    lodging establishment names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.53
     Meksiku
    -0.52
    SequentialGroup
    -0.51
    RefNanny
    -0.49
     '\\;'
    -0.49
    riwal
    -0.48
     незавершена
    -0.48
    PreferredItem
    -0.47
     Taktlose
    -0.47
     noDo
    -0.46
    POSITIVE LOGITS
     hotel
    0.81
     Hotel
    0.73
     hotels
    0.64
    Hotel
    0.62
    hotel
    0.61
     motel
    0.59
     Hotels
    0.56
     inn
    0.54
     Inn
    0.53
     HOTEL
    0.52
    Act Density 0.075%

    No Known Activations