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

    Neuronpedia

    INDEX
    Explanations

    getting things done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রাপ্ত
    0.32
    ர்
    0.32
    關於
    0.30
     เศษ
    0.29
    <0xE2>
    0.28
     terdapat
    0.28
     الطل
    0.28
     Comprehensive
    0.28
     กำ
    0.28
     achieving
    0.27
    POSITIVE LOGITS
     done
    0.55
     funcionando
    0.54
     lined
    0.52
     underway
    0.52
     sorted
    0.51
     outta
    0.50
     ready
    0.49
     pronta
    0.48
     into
    0.48
     out
    0.46
    Act Density 0.014%

    No Known Activations