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

    Neuronpedia

    INDEX
    Explanations

    Japanese particles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oding
    -0.07
    artist
    -0.07
     /*----------------------------------------------------------------
    -0.07
    =?,
    -0.06
    scription
    -0.06
    payload
    -0.06
    лин
    -0.06
    istr
    -0.06
    .Require
    -0.06
    _pv
    -0.06
    POSITIVE LOGITS
     مصر
    0.08
    Speaker
    0.06
    诗
    0.06
    ثر
    0.06
    الش
    0.06
    허
    0.06
     MIL
    0.06
    新闻
    0.06
    шими
    0.06
     shattered
    0.06
    Act Density 0.059%

    No Known Activations