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

    Neuronpedia

    INDEX
    Explanations

    bubble sort algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    1.02
    om
    0.90
    as
    0.89
    п
    0.84
    a
    0.84
    u
    0.83
    of
    0.82
    ob
    0.81
    га
    0.80
    o
    0.80
    POSITIVE LOGITS
    िनेट
    1.02
    󰡕
    1.01
     numérique
    1.00
     informée
    0.99
     oluşan
    0.99
     arrhythmias
    0.97
     roja
    0.96
    mêmes
    0.95
     Astrophys
    0.94
    )`;
    0.94
    Act Density 0.001%

    No Known Activations