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

    Neuronpedia

    INDEX
    Explanations

    brene brown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unele
    0.46
    さんの
    0.42
    '
    0.40
    ター
    0.40
    오
    0.40
    ランク
    0.39
    ളി
    0.39
    挙げ
    0.38
    谙
    0.38
     സി
    0.38
    POSITIVE LOGITS
     społec
    0.47
    ार्मिक
    0.45
    ကာ
    0.43
     stadion
    0.42
    🏚
    0.42
     পৌ
    0.42
    ……..
    0.42
     ∣
    0.41
    식회사
    0.41
    🏛
    0.41
    Act Density 0.002%

    No Known Activations