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

    Neuronpedia

    INDEX
    Explanations

    share, control, resources, advocate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.52
    โดย
    0.49
    स
    0.49
    科
    0.46
    ()\
    0.46
    ݢ
    0.45
    前
    0.45
    最
    0.45
    スポーツ
    0.45
     यात
    0.45
    POSITIVE LOGITS
     beng
    0.48
     brutality
    0.47
     ripening
    0.47
     machining
    0.46
     zebra
    0.46
     harvesting
    0.46
     Rebellion
    0.46
     menstruation
    0.45
     washing
    0.45
     Zebra
    0.45
    Act Density 0.000%

    No Known Activations