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

    Neuronpedia

    INDEX
    Explanations

    Apple Watch build tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gave
    0.41
     chav
    0.41
     surprised
    0.39
     adjusts
    0.38
     suddenly
    0.37
    িতা
    0.37
     पढ़ें
    0.37
     Fans
    0.37
     ליי
    0.37
     Suddenly
    0.36
    POSITIVE LOGITS
    行業
    0.45
    業界
    0.43
     compone
    0.41
    jsdel
    0.39
    eligible
    0.38
    行业
    0.38
    LOTRE
    0.38
    workItem
    0.38
    行业的
    0.38
     отрасли
    0.37
    Act Density 0.004%

    No Known Activations