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

    Neuronpedia

    INDEX
    Explanations

    EventBridge, essential, Spark, mention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ხელისუფ
    0.41
    朊
    0.38
    SXml
    0.38
     당연
    0.38
     กี้
    0.38
    骯
    0.38
    на
    0.38
    孛
    0.38
    ánto
    0.37
    <unused314>
    0.37
    POSITIVE LOGITS
    0.57
    5
    0.50
     E
    0.48
    6
    0.47
     a
    0.44
    0
    0.43
    8
    0.43
     D
    0.42
     N
    0.42
     L
    0.41
    Act Density 0.278%

    No Known Activations