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

    Neuronpedia

    INDEX
    Explanations

    requests and announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     होता
    0.44
     phrasing
    0.43
     context
    0.41
     وقلنا
    0.40
     يصير
    0.40
     Basically
    0.40
     dapp
    0.40
    もあった
    0.40
     Actually
    0.40
     其实
    0.40
    POSITIVE LOGITS
     anunció
    0.97
     anunciou
    0.80
     announced
    0.79
     recently
    0.77
     announces
    0.76
    recently
    0.75
    宣布
    0.74
    announced
    0.73
     Announces
    0.73
     объяви
    0.73
    Act Density 0.041%

    No Known Activations