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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations or tourist destinations

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

    Followed by location-related terms

    np_acts-logits-general · gemini-2.0-flash

    places and their administrative divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cebu
    -0.62
     Recife
    -0.61
     Houſe
    -0.61
     Davao
    -0.56
     Puget
    -0.54
     Penang
    -0.53
     Anſ
    -0.53
     Azo
    -0.52
     Amarillo
    -0.52
     Spokane
    -0.52
    POSITIVE LOGITS
     '\\;'
    0.83
    Tikang
    0.76
     surla
    0.72
     createSprite
    0.71
    Personensuche
    0.69
     TextInputType
    0.68
     cherchés
    0.68
    ItemBackground
    0.67
     MainAxisSize
    0.65
    fromnode
    0.65
    Act Density 0.338%

    No Known Activations