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

    Neuronpedia

    INDEX
    Explanations

    sitting down or in a place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    laid
    0.75
     standing
    0.73
     lying
    0.71
     berdiri
    0.71
    Spending
    0.70
     seated
    0.70
    हान
    0.68
    held
    0.66
     alternatively
    0.66
    lukan
    0.66
    POSITIVE LOGITS
     bolt
    0.95
    elite
    0.94
     ducks
    0.93
     amet
    0.93
    élite
    0.90
     tight
    0.88
     Ducks
    0.83
     MongoClient
    0.80
     Tight
    0.79
    िजन
    0.79
    Act Density 0.140%

    No Known Activations