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

    Neuronpedia

    INDEX
    Explanations

    defining characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     문제가
    0.47
    problem
    0.43
    assume
    0.42
     সমস্যার
    0.41
     مسئلہ
    0.40
     problème
    0.40
    fehler
    0.39
     problemas
    0.39
     సమస్య
    0.39
    Assume
    0.38
    POSITIVE LOGITS
     history
    0.70
     origins
    0.69
     geography
    0.63
     characteristics
    0.61
     Origins
    0.60
    history
    0.58
     appearance
    0.57
     características
    0.57
     Characteristics
    0.54
    Origins
    0.54
    Act Density 0.006%

    No Known Activations