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

    Neuronpedia

    INDEX
    Explanations

    genres and media descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    网上
    0.75
    门店
    0.71
    лева
    0.70
    求め
    0.69
    氏は
    0.66
     uptake
    0.66
     केंद
    0.65
    মাত
    0.65
    ཏ
    0.63
     შესახებ
    0.63
    POSITIVE LOGITS
     thriller
    1.62
    comedy
    1.25
    喜剧
    1.18
     comedies
    1.15
    fantasy
    1.08
     adventure
    1.08
     comedy
    1.07
     fantasy
    1.07
    genre
    1.07
    horror
    1.06
    Act Density 0.888%

    No Known Activations