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

    Neuronpedia

    INDEX
    Explanations

    words after data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ሽፋ
    0.42
    ยิ่ง
    0.38
     ህ
    0.38
    に加え
    0.38
     служ
    0.37
     soud
    0.37
     justiça
    0.37
     ছাড়াও
    0.37
    ଙ
    0.37
    bing
    0.36
    POSITIVE LOGITS
    digit
    0.47
     või
    0.46
     digit
    0.42
    டல்
    0.41
    데이
    0.41
     erinn
    0.41
     पद्धति
    0.40
     njima
    0.40
     کردیا
    0.40
    0.40
    Act Density 0.007%

    No Known Activations