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

    Neuronpedia

    INDEX
    Explanations

    hull structure design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nect
    0.42
     bunt
    0.40
    batch
    0.37
    Nes
    0.37
    道
    0.37
    arnings
    0.37
     Nellie
    0.37
    PCM
    0.36
    meter
    0.35
    frak
    0.35
    POSITIVE LOGITS
     قل
    0.40
    ='/'
    0.40
    ወሰ
    0.40
    Ster
    0.38
     Ster
    0.38
     வய
    0.37
     কোয়া
    0.37
     স্টার
    0.35
    ıya
    0.35
    windowFixedWidth
    0.35
    Act Density 0.002%

    No Known Activations