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

    Neuronpedia

    INDEX
    Explanations

    future DVTs or proactive measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subTest
    0.40
    隐含规则
    0.38
    大致
    0.38
     ['(?
    0.38
    找不到
    0.37
     auxqu
    0.37
    រក
    0.37
    無需
    0.35
    jdbcType
    0.35
     carbonyl
    0.35
    POSITIVE LOGITS
     sinned
    0.42
    افر
    0.39
    ajal
    0.39
     있어야
    0.38
     anim
    0.38
    ेंगी
    0.38
     Unternehmer
    0.38
    Editing
    0.38
     kontra
    0.38
     suced
    0.38
    Act Density 0.002%

    No Known Activations