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

    Neuronpedia

    INDEX
    Explanations

    future possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ospitals
    0.69
    begin
    0.66
    overlapping
    0.61
    0.59
    把自己
    0.58
    を開始
    0.58
     fled
    0.57
    특히
    0.57
    renerg
    0.57
    (\{
    0.56
    POSITIVE LOGITS
     whether
    1.27
     Whether
    1.18
    Whether
    1.10
     apakah
    1.07
    今後の
    1.06
    whether
    0.94
     future
    0.93
    未來
    0.89
     Future
    0.89
     Hopefully
    0.86
    Act Density 0.006%

    No Known Activations