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

    Neuronpedia

    INDEX
    Explanations

    AI model names and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #######
    0.38
    ರ್ಯ
    0.35
     attribut
    0.35
    ្នក
    0.34
    ヤモンド
    0.34
     общества
    0.33
     مردم
    0.33
    ญิง
    0.33
    ຈັດສົ່ງ
    0.33
    ChangeString
    0.33
    POSITIVE LOGITS
     II
    0.72
     III
    0.69
    II
    0.66
    III
    0.61
    系列
    0.58
     series
    0.56
    ™
    0.55
    系列的
    0.51
     variants
    0.50
     Plus
    0.49
    Act Density 0.111%

    No Known Activations