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

    Neuronpedia

    INDEX
    Explanations

    dataset of text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    datasets
    0.43
     Scatter
    0.43
     Dataset
    0.43
     JESUS
    0.42
     retard
    0.42
     nausea
    0.42
    dataset
    0.41
     Biblia
    0.39
     scat
    0.39
     DataSet
    0.39
    POSITIVE LOGITS
    オンライン
    0.41
     online
    0.40
    Online
    0.40
    atino
    0.40
     webpages
    0.39
     common
    0.38
    前辈
    0.38
    のは
    0.37
     доку
    0.37
     интернет
    0.37
    Act Density 0.007%

    No Known Activations