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

    Neuronpedia

    INDEX
    Explanations

    data from response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     высоких
    0.40
    ushchev
    0.38
    椁
    0.37
     조선
    0.36
    Anime
    0.35
     anime
    0.35
    DNF
    0.34
    facial
    0.34
    Interfaces
    0.34
    億円
    0.33
    POSITIVE LOGITS
     data
    1.46
    data
    1.38
    数据
    1.18
    データ
    1.16
     DATA
    1.11
     डेटा
    1.11
     Data
    1.08
     डाटा
    1.07
     데이터
    1.05
    Data
    1.01
    Act Density 0.002%

    No Known Activations