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

    Neuronpedia

    INDEX
    Explanations

    progress and change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     animations
    0.29
     noting
    0.29
     Retina
    0.29
     Logic
    0.29
     interactivity
    0.28
    ダイエット
    0.27
     Kanban
    0.27
     headaches
    0.27
     files
    0.27
     inserts
    0.27
    POSITIVE LOGITS
     પોતાના
    0.34
     propria
    0.31
    лас
    0.29
     своими
    0.28
    тельного
    0.28
     proprie
    0.27
     સાથે
    0.27
    创造
    0.26
    תן
    0.26
    ujourd
    0.26
    Act Density 0.282%

    No Known Activations