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

    Neuronpedia

    INDEX
    Explanations

    says

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ingestion
    -0.07
     заб
    -0.07
    anguages
    -0.07
    >Z
    -0.06
     kapı
    -0.06
    _IC
    -0.06
     astore
    -0.06
    /notification
    -0.06
    ------------↵
    -0.06
    \Catalog
    -0.06
    POSITIVE LOGITS
    ל
    0.07
     Treasure
    0.07
    import
    0.06
    PLAY
    0.06
    .util
    0.06
    にある
    0.06
     hash
    0.06
    oky
    0.06
    (sql
    0.06
    .gsub
    0.06
    Act Density 0.032%

    No Known Activations