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

    Neuronpedia

    INDEX
    Explanations

    arithmetic mean, reducing substance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lü
    0.47
    hearted
    0.46
    ो
    0.43
     நெரு
    0.42
    bonding
    0.42
     estimés
    0.42
    ̎
    0.42
    пу
    0.42
     as
    0.42
    pressure
    0.41
    POSITIVE LOGITS
    ઠા
    0.45
     VISA
    0.45
     unicode
    0.44
    创建一个
    0.44
    وية
    0.43
    క్షణ
    0.42
    す
    0.42
    関連
    0.41
    部份
    0.41
    䂧
    0.41
    Act Density 0.001%

    No Known Activations