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

    Neuronpedia

    INDEX
    Explanations

    explaining or asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    性と
    0.82
    성과
    0.82
    における
    0.81
    かつ
    0.80
     topographical
    0.75
    TableRow
    0.74
     topography
    0.72
    Executed
    0.72
    มนเชสเตอร์
    0.72
    最も
    0.71
    POSITIVE LOGITS
     omdat
    1.00
     เพราะ
    0.94
     :/
    0.92
     because
    0.91
     :)
    0.88
     BECAUSE
    0.87
     😂
    0.87
     :(
    0.84
     obwohl
    0.82
     haha
    0.82
    Act Density 0.093%

    No Known Activations