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

    Neuronpedia

    INDEX
    Explanations

    explaining or describing beams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пя
    0.41
     TCM
    0.40
    ເພ
    0.39
     cyberspace
    0.39
    ста
    0.39
     bilhões
    0.38
     MAKE
    0.38
    methanol
    0.38
     kimia
    0.37
    antai
    0.37
    POSITIVE LOGITS
     açıklam
    0.42
     توضیح
    0.42
     sermon
    0.41
     వివ
    0.40
    Explained
    0.40
    怎
    0.40
     preached
    0.40
     설명
    0.40
     বেশ
    0.37
    的声音
    0.37
    Act Density 0.001%

    No Known Activations