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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and facilities

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

    building sections and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PROVID
    -0.36
     sako
    -0.33
     Defensa
    -0.33
    znych
    -0.31
     tourisme
    -0.30
     พร
    -0.30
     gerek
    -0.30
    家が
    -0.30
     hakk
    -0.29
    Provider
    -0.29
    POSITIVE LOGITS
     upstairs
    0.66
     downstairs
    0.64
    parsedMessage
    0.61
     esternos
    0.58
     rooms
    0.58
    Rooms
    0.58
     ویکی‌پدی
    0.57
     Rooms
    0.57
    room
    0.55
    rooms
    0.54
    Act Density 0.024%

    No Known Activations