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

    Neuronpedia

    INDEX
    Explanations

    Mastering skills and crafts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    体现
    0.46
     menjalani
    0.45
    Master
    0.44
    毕
    0.43
    训练
    0.42
    master
    0.42
     Master
    0.41
    Row
    0.40
    ﺂ
    0.40
    зад
    0.40
    POSITIVE LOGITS
     vowel
    0.50
     dialects
    0.46
     địa
    0.46
    )}(\
    0.45
     tracheal
    0.45
     islet
    0.44
     sofas
    0.43
     reversals
    0.43
     algal
    0.43
     الاثنين
    0.43
    Act Density 0.001%

    No Known Activations