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

    Neuronpedia

    INDEX
    Explanations

    geographical names and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Agricultura
    0.39
     Brahma
    0.37
    lng
    0.36
    ne
    0.35
     Madera
    0.35
     Instance
    0.35
    ↵↵
    0.34
     Existing
    0.34
     Thirteen
    0.34
     Alpha
    0.33
    POSITIVE LOGITS
    :
    0.53
    >
    0.52
    =
    0.48
    ：
    0.46
    स
    0.45
     domande
    0.44
     esso
    0.43
    س
    0.43
    ۹
    0.42
     meny
    0.41
    Act Density 0.198%

    No Known Activations