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

    Neuronpedia

    INDEX
    Explanations

    references to amusement park attractions

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

    entertainment or amusement

    np_acts-logits-general · gemini-2.0-flash

    amusement rides and ropes courses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijani
    -0.70
     Paglinawan
    -0.67
    EDEFAULT
    -0.67
     كومونز
    -0.66
     تضيفلها
    -0.65
     فريبيس
    -0.65
    lgari
    -0.64
     oprot
    -0.62
     Италијани
    -0.61
    Хьажоргаш
    -0.58
    POSITIVE LOGITS
     rides
    1.23
     ride
    1.11
     Rides
    0.97
     amusement
    0.94
    rides
    0.93
    ride
    0.85
     slides
    0.84
     Ride
    0.83
    Ride
    0.83
     slide
    0.83
    Act Density 0.158%

    No Known Activations