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

    Neuronpedia

    INDEX
    Explanations

    game scores and victories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     సంస్థ
    0.35
     superfici
    0.35
     kullanım
    0.34
    年
    0.34
     sistemi
    0.33
     زیرمه
    0.33
     soggetti
    0.32
    ফটেন
    0.32
     Lebensmittel
    0.32
     Dateien
    0.32
    POSITIVE LOGITS
     scoring
    0.47
    scoring
    0.44
     shutout
    0.44
     victory
    0.42
     scored
    0.41
     victories
    0.40
     touchdowns
    0.39
     score
    0.39
     scoreless
    0.39
    score
    0.36
    Act Density 0.013%

    No Known Activations