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

    Neuronpedia

    INDEX
    Explanations

    describing qualities, data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שי
    0.49
     כדי
    0.41
     שנ
    0.41
    findContacts
    0.40
     זי
    0.40
     لدى
    0.39
     ზ
    0.39
    ocks
    0.38
     اور
    0.38
     disagreement
    0.38
    POSITIVE LOGITS
     estudiantes
    0.48
     Trials
    0.46
     ouvr
    0.46
     semplice
    0.44
     promos
    0.44
     finalists
    0.44
     unrival
    0.44
    স্বরূপ
    0.43
     jugs
    0.43
     cał
    0.43
    Act Density 0.003%

    No Known Activations