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

    Neuronpedia

    INDEX
    Explanations

    scoring goals and goalscorers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chowdh
    0.47
     parametr
    0.40
    寿命
    0.39
     парамет
    0.39
    考验
    0.39
    掺
    0.38
    鿢
    0.38
     കാലാവ
    0.37
    摻
    0.37
     khảo
    0.36
    POSITIVE LOGITS
     scoring
    1.95
     scored
    1.80
     Scoring
    1.66
     scorer
    1.59
     scorers
    1.59
    scoring
    1.58
     score
    1.47
    scored
    1.44
    得分
    1.37
    scorer
    1.30
    Act Density 0.013%

    No Known Activations