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

    Neuronpedia

    INDEX
    Explanations

    months is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    0.44
    Ри
    0.43
    Webster
    0.43
    JW
    0.41
    во
    0.40
     јуну
    0.40
    ग़
    0.40
    राबरी
    0.40
    IO
    0.40
    Amsterdam
    0.39
    POSITIVE LOGITS
     donné
    0.47
     κ
    0.45
    raphe
    0.45
     Raise
    0.44
     എന്ന
    0.42
     لأنه
    0.42
     কয়েকজন
    0.41
     introdu
    0.40
     koj
    0.40
     FCS
    0.40
    Act Density 0.001%

    No Known Activations