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

    Neuronpedia

    INDEX
    Explanations

    and followed by confidential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     david
    0.37
     Derr
    0.37
     vok
    0.36
    etok
    0.36
     axis
    0.36
     Derrick
    0.35
    David
    0.35
     lan
    0.35
    W
    0.34
     Derek
    0.34
    POSITIVE LOGITS
     بگ
    0.39
     เนื้อ
    0.36
    เนื้อ
    0.34
     мате
    0.34
    льники
    0.34
     নাঁ
    0.33
    Ҷ
    0.33
    薢
    0.33
     वर्त
    0.33
     Пла
    0.33
    Act Density 0.006%

    No Known Activations