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

    Neuronpedia

    INDEX
    Explanations

    unity game engine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diam
    0.63
     opposite
    0.56
    opposite
    0.49
     Opposite
    0.48
    diam
    0.47
    Diam
    0.47
     vertically
    0.46
     opposing
    0.46
    aligned
    0.45
    bene
    0.44
    POSITIVE LOGITS
    yatiti
    0.46
     Unity
    0.43
    メートル
    0.43
    オブ
    0.39
    マト
    0.38
    效益
    0.38
    团结
    0.38
    游戏
    0.38
    坨
    0.38
    ভ্র
    0.37
    Act Density 0.002%

    No Known Activations