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

    Neuronpedia

    INDEX
    Explanations

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bowiem
    0.49
    Denn
    0.47
     totiž
    0.45
    毕竟
    0.44
     Bởi
    0.42
     없는
    0.41
    Frozen
    0.40
     değildir
    0.40
    ということです
    0.40
     preferably
    0.39
    POSITIVE LOGITS
    請問
    1.09
    怎么办
    1.05
     Why
    1.03
     ماذا
    1.02
     why
    1.01
     क्या
    1.00
     What
    0.96
     क्‍या
    0.96
     શું
    0.94
    はどう
    0.94
    Act Density 0.008%

    No Known Activations