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

    Neuronpedia

    INDEX
    Explanations

    words that are frequently used as prepositions

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     for
    -0.75
     to
    -0.74
     of
    -0.72
     مشين
    -0.71
    AndroidJUnit
    -0.71
     from
    -0.63
     Without
    -0.62
     with
    -0.62
    tagHelperRunner
    -0.61
     وتسجيلات
    -0.61
    POSITIVE LOGITS
    ImageContext
    0.61
     düğün
    0.57
     Jove
    0.56
     torchvision
    0.55
    at
    0.53
     doInBackground
    0.53
     copii
    0.52
     skimage
    0.52
     piele
    0.52
     soldati
    0.51
    Act Density 27.259%

    No Known Activations