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

    Neuronpedia

    INDEX
    Explanations

    numerical values and statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     paramètres
    0.40
    데이터
    0.39
    ۳
    0.38
    参数
    0.38
    Лі
    0.37
     सॉल्यू
    0.36
    เส้น
    0.36
    总结
    0.35
     catégorie
    0.35
     supprimer
    0.35
    POSITIVE LOGITS
     million
    0.51
     billionaires
    0.51
     milhões
    0.50
     millions
    0.48
     billion
    0.48
     billions
    0.46
     trillion
    0.46
     trillions
    0.46
     میلیون
    0.45
     milioni
    0.44
    Act Density 0.001%

    No Known Activations