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

    Neuronpedia

    INDEX
    Explanations

    LA or La words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ShaderType
    0.42
     secretNumber
    0.35
     ګ
    0.34
    uluk
    0.34
     Elkus
    0.34
     nirvach
    0.34
     draggable
    0.33
    鍑
    0.33
    麋
    0.33
    TreeNavigator
    0.33
    POSITIVE LOGITS
     LA
    3.47
    LA
    3.34
    La
    2.66
    la
    2.53
     ला
    2.53
     Ла
    2.52
     La
    2.48
     la
    2.47
     ла
    2.41
     Laura
    2.41
    Act Density 0.033%

    No Known Activations