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

    Neuronpedia

    INDEX
    Explanations

    2 followed by 6

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kotlin
    0.33
     kotlin
    0.33
    特に
    0.32
     soms
    0.32
     biến
    0.32
     thẩm
    0.32
    গণ
    0.31
    ুরা
    0.31
    的一些
    0.31
    处理器
    0.31
    POSITIVE LOGITS
     Antes
    0.49
     Therefore
    0.47
     Before
    0.47
     پہلے
    0.47
     préal
    0.47
    が必要です
    0.47
    Therefore
    0.46
     préalable
    0.46
    셔야
    0.45
     BEFORE
    0.44
    Act Density 0.404%

    No Known Activations