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

    Neuronpedia

    INDEX
    Explanations

    space bar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    极端
    0.42
    erc
    0.41
    sees
    0.41
    টে
    0.40
    원에
    0.40
    iless
    0.40
    extreme
    0.39
     ము
    0.38
    罩
    0.38
    controller
    0.36
    POSITIVE LOGITS
    Space
    0.76
     Space
    0.69
     SPACE
    0.67
     space
    0.62
     spazio
    0.60
     espacio
    0.60
    space
    0.59
    SPACE
    0.57
    スペース
    0.56
     स्पेस
    0.56
    Act Density 0.001%

    No Known Activations