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

    Neuronpedia

    INDEX
    Explanations

    center of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dimension
    0.46
    ার্জন
    0.41
    ominator
    0.37
    ιών
    0.37
     drz
    0.37
     ఉపయోగ
    0.37
    جن
    0.36
     chuyện
    0.36
    Corner
    0.36
    횐
    0.36
    POSITIVE LOGITS
     centro
    0.68
     центр
    0.66
    Centro
    0.66
     center
    0.63
     中心
    0.62
     centr
    0.62
     centrally
    0.62
     centrality
    0.61
     centri
    0.61
     centrale
    0.60
    Act Density 0.057%

    No Known Activations