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

    Neuronpedia

    INDEX
    Explanations

    punctuations followed by 😊

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    1.39
    我
    1.31
    I
    1.16
     我
    1.12
    我要
    1.11
    私は
    1.11
     Tôi
    1.11
     আমি
    1.09
     tôi
    1.08
    私が
    1.03
    POSITIVE LOGITS
     Ultimately
    0.87
    Ultimately
    0.87
     Leveraging
    0.86
     building
    0.83
    ifting
    0.83
     Between
    0.82
     Spending
    0.81
     Utilizing
    0.81
     recreating
    0.81
     shifting
    0.81
    Act Density 0.007%

    No Known Activations