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

    Neuronpedia

    INDEX
    Explanations

    what kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ofthe
    0.83
     của
    0.82
    របស់
    0.80
     ofthe
    0.76
    ຂອງ
    0.70
     delle
    0.66
    čkog
    0.65
    ಥವಾ
    0.62
    ቱም
    0.61
    రీలు
    0.61
    POSITIVE LOGITS
     fo
    0.80
     off
    0.68
     pf
    0.63
    <0xC2>
    0.62
     od
    0.58
      
    0.57
     os
    0.56
     ​​
    0.55
    <unused2197>
    0.53
     ot
    0.51
    Act Density 0.781%

    No Known Activations