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

    Neuronpedia

    INDEX
    Explanations

    preposition followed by a noun/adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ம்
    2.06
    س
    1.79
    Más
    1.44
    8
    1.44
    ע
    1.44
    ہ
    1.39
    j
    1.38
    7
    1.37
     उसमें
    1.36
    ам
    1.35
    POSITIVE LOGITS
     وفي
    1.99
    부터
    1.63
    ا
    1.62
    客様
    1.52
     kojem
    1.48
    ı
    1.48
    ılarak
    1.47
    外的
    1.40
    いきます
    1.40
    IERC
    1.40
    Act Density 1.056%

    No Known Activations