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

    Neuronpedia

    INDEX
    Explanations

    convert to or from units and currencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ชื่อ
    0.35
    Adobe
    0.34
    MAX
    0.33
    Gal
    0.33
     नामित
    0.32
    reihe
    0.32
     quite
    0.32
    FROM
    0.31
    frontend
    0.31
    ipers
    0.31
    POSITIVE LOGITS
     в
    0.42
     în
    0.40
    क्टूबर
    0.39
     }>;
    0.38
    月中
    0.37
     अक्टूबर
    0.37
    日在
    0.37
     ㅎ
    0.36
    ្នុង
    0.36
     nella
    0.36
    Act Density 0.001%

    No Known Activations