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

    Neuronpedia

    INDEX
    Explanations

    code identifiers and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    決して
    0.31
    longer
    0.30
     ወይም
    0.29
     சிலர்
    0.29
     гаранти
    0.29
    <unused97>
    0.28
    并不是
    0.27
     მხოლოდ
    0.27
    広が
    0.27
    只限
    0.27
    POSITIVE LOGITS
     thofe
    0.31
    usin
    0.29
     কিভাবে
    0.28
    欤
    0.27
    рот
    0.26
    GameObject
    0.26
    的的
    0.26
    𝐨
    0.26
     stratégies
    0.26
    zca
    0.26
    Act Density 0.232%

    No Known Activations