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

    Neuronpedia

    INDEX
    Explanations

    windows and glass details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    枞
    0.83
    捧
    0.80
    蕲
    0.75
     హీరో
    0.75
    mesinin
    0.73
     enzimas
    0.69
    낵
    0.69
    endedor
    0.67
    വുമായി
    0.67
     tvam
    0.67
    POSITIVE LOGITS
     glass
    2.67
     window
    2.30
     windows
    2.28
     Glass
    2.28
    Glass
    2.28
    glass
    2.24
    玻璃
    2.22
     panes
    2.11
     Window
    2.06
     kaca
    1.99
    Act Density 0.083%

    No Known Activations