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

    Neuronpedia

    INDEX
    Explanations

    Tiger Woods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Auch
    -1.02
    — 
    -0.96
    ＞＞
    -0.96
     reloadData
    -0.95
    你们
    -0.90
     großen
    -0.89
    他们
    -0.89
    ;");
    -0.88
    =“
    -0.88
    sprogram
    -0.87
    POSITIVE LOGITS
    ennies
    1.12
     Wednesdays
    1.08
     SaaS
    1.07
    过来了
    1.05
    っており
    1.04
     Tuesdays
    1.03
    らせ
    1.01
     mln
    0.98
     Mondays
    0.98
    INTR
    0.98
    Act Density 0.008%

    No Known Activations