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

    Neuronpedia

    INDEX
    Explanations

    food items and accompaniments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oficiais
    0.99
     finales
    0.96
    лизи
    0.95
    و
    0.95
    КИ
    0.93
    রের
    0.93
     "\(
    0.92
     Epsom
    0.92
     espèce
    0.92
    eren
    0.90
    POSITIVE LOGITS
    wood
    1.11
    legs
    1.05
    works
    1.00
    dancer
    0.99
    hearts
    0.99
    Ideally
    0.97
    IEnumerable
    0.95
    テナンス
    0.95
    feather
    0.94
    field
    0.93
    Act Density 0.279%

    No Known Activations