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

    Neuronpedia

    INDEX
    Explanations

    engage in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     R
    0.39
     support
    0.36
     Kon
    0.36
     r
    0.34
               
    0.34
    <h3>
    0.34
     Winter
    0.34
          
    0.33
     través
    0.33
     Roma
    0.33
    POSITIVE LOGITS
     ಯಾವ
    0.44
    ၆
    0.41
    预测
    0.39
     predicting
    0.38
    毉
    0.38
     言っ
    0.37
    oleic
    0.37
     ਉਹ
    0.36
    峎
    0.36
    ដែល
    0.36
    Act Density 0.000%

    No Known Activations