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

    Neuronpedia

    INDEX
    Explanations

    political ideology or specific information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    товый
    0.46
     安全
    0.46
    类别
    0.45
     স্বাগত
    0.45
     የቀ
    0.45
    xcuserdata
    0.44
    固体
    0.44
    ություններ
    0.43
    ())));
    0.43
    司机
    0.43
    POSITIVE LOGITS
    d
    0.58
    ed
    0.56
    Dec
    0.52
    Can
    0.52
    ine
    0.51
    More
    0.51
    s
    0.51
    ll
    0.50
    -
    0.50
    al
    0.47
    Act Density 0.001%

    No Known Activations