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

    Neuronpedia

    INDEX
    Explanations

    mid +

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opies
    1.03
    将
    0.98
    ۀ
    0.98
    ances
    0.90
    boolean
    0.90
    objects
    0.89
    slot
    0.88
    פ
    0.87
     dira
    0.87
    Hash
    0.87
    POSITIVE LOGITS
     eCommerce
    1.24
     просмо
    1.20
     biofilm
    1.13
    ра
    1.12
     Gastroenter
    1.10
    医疗
    1.09
     actionable
    1.08
     económico
    1.07
     pediatric
    1.07
     classico
    1.06
    Act Density 0.002%

    No Known Activations