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

    Neuronpedia

    INDEX
    Explanations

    bring back memories or API sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appunto
    0.40
     مذکور
    0.34
     njima
    0.31
     derfor
    0.30
     divulg
    0.29
     supprimer
    0.29
     aceste
    0.28
     właśnie
    0.28
    रिमेंट
    0.28
     quei
    0.28
    POSITIVE LOGITS
     ,
    0.29
    ;,
    0.29
     C
    0.28
    *,
    0.28
     ，
    0.28
    世界
    0.28
    fast
    0.27
    u
    0.27
    はもちろん
    0.27
    었고
    0.27
    Act Density 0.197%

    No Known Activations