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

    Neuronpedia

    INDEX
    Explanations

    making it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     because
    0.47
     থাকলে
    0.45
    因為
    0.44
     pretože
    0.42
     क्योंकि
    0.40
     karena
    0.40
    因为
    0.39
    arrow
    0.39
     کیونکہ
    0.39
     因為
    0.38
    POSITIVE LOGITS
    popupTheme
    0.43
    簹
    0.39
     it
    0.37
     jt
    0.37
     Беларусь
    0.37
    यहाँ
    0.36
     reconstru
    0.36
     customPlot
    0.36
     полноцен
    0.35
     देम
    0.35
    Act Density 0.008%

    No Known Activations