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

    Neuronpedia

    INDEX
    Explanations

    heavy [qualifier]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    1.79
    า
    1.52
    々
    1.26
    یر
    1.23
    ە
    1.23
    ो
    1.20
    ா
    1.20
    ール
    1.13
    kę
    1.13
    ına
    1.12
    POSITIVE LOGITS
    '
    1.17
    h
    1.08
    -
    1.06
    <0x91>
    1.05
    重
    1.01
     laden
    1.00
     heavier
    0.98
     pesante
    0.96
    要
    0.96
     Schwer
    0.95
    Act Density 0.023%

    No Known Activations