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

    Neuronpedia

    INDEX
    Explanations

    code and programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    闪烁
    -0.68
    鐙
    -0.65
     Tina
    -0.64
    流动
    -0.64
    drawSprites
    -0.63
    平台
    -0.63
    GERY
    -0.63
     Two
    -0.63
    ۚ
    -0.63
     químicas
    -0.60
    POSITIVE LOGITS
    HOW
    0.66
    曼
    0.66
     Charcoal
    0.66
    Reco
    0.65
     clicked
    0.65
    ក
    0.64
     τού
    0.63
     控制
    0.63
     Adagio
    0.63
     Warszawie
    0.62
    Act Density 0.094%

    No Known Activations