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

    Neuronpedia

    INDEX
    Explanations

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DevOps
    0.46
    지
    0.42
     Runnable
    0.42
     krat
    0.42
     intel
    0.41
     pixel
    0.41
     inline
    0.40
     DirectX
    0.39
     backend
    0.39
     blob
    0.38
    POSITIVE LOGITS
     melaksanakan
    0.58
     üç
    0.51
     danske
    0.51
     eerste
    0.50
     tweede
    0.50
     daerah
    0.50
     melindungi
    0.50
     mengatakan
    0.49
     dünyanın
    0.49
     ünlü
    0.48
    Act Density 0.006%

    No Known Activations