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

    Neuronpedia

    INDEX
    Explanations

    foreign or multilingual context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.58
    ق
    0.54
    7
    0.50
    6
    0.46
    linking
    0.46
    5
    0.46
    ４
    0.45
    Egyptian
    0.45
    important
    0.45
     ghat
    0.44
    POSITIVE LOGITS
    એસ
    0.46
     valutazione
    0.44
     extranj
    0.44
     ট্রেনে
    0.43
     买
    0.43
     иностран
    0.42
    MathMarks
    0.42
     различ
    0.42
     রোল
    0.42
     بیاکت
    0.41
    Act Density 0.005%

    No Known Activations