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

    Neuronpedia

    INDEX
    Explanations

    trained on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Suck
    0.40
     Torres
    0.39
    諡
    0.39
    पे
    0.38
     sucking
    0.38
    ảnh
    0.37
     echoed
    0.37
     suck
    0.37
     knelt
    0.37
     mill
    0.37
    POSITIVE LOGITS
     النمو
    0.39
     থেকেই
    0.37
     Tik
    0.37
    र्दू
    0.37
     tickers
    0.37
     Tessa
    0.37
    leun
    0.36
     Lankan
    0.35
    出自
    0.35
     Blas
    0.35
    Act Density 0.004%

    No Known Activations