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

    Neuronpedia

    INDEX
    Explanations

    queue and explore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pras
    0.47
    Х
    0.46
    П
    0.45
    कुछ
    0.43
    В
    0.42
    某
    0.41
    Một
    0.40
    стойчи
    0.39
    wow
    0.39
    那
    0.39
    POSITIVE LOGITS
     तुमने
    0.47
    \)
    0.42
     ሰ
    0.42
     ඔබේ
    0.40
     demonstrates
    0.40
     betrayal
    0.39
    ImageQueue
    0.39
     Damage
    0.38
     וא
    0.38
     समापन
    0.38
    Act Density 0.001%

    No Known Activations