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

    Neuronpedia

    INDEX
    Explanations

    style, creative, market, block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <?
    0.39
     lub
    0.36
     ch
    0.36
     <-
    0.36
    皇后
    0.35
     benef
    0.35
    צות
    0.35
     city
    0.34
    \,
    0.33
     vada
    0.33
    POSITIVE LOGITS
     पीछ
    0.43
    起了
    0.41
    背景
    0.40
     ತಯಾರ
    0.38
     ಕಾಂಗ್ರೆ
    0.38
    􀂃
    0.38
    backgroundImage
    0.38
    CameraController
    0.37
    στημα
    0.37
     оці
    0.37
    Act Density 0.004%

    No Known Activations