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

    Neuronpedia

    INDEX
    Explanations

    breaking down complex topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    建议
    0.48
     suggested
    0.41
     Software
    0.39
     Suggested
    0.39
     Release
    0.38
     Tissue
    0.38
    只需
    0.38
     Light
    0.37
     Tool
    0.37
     Duplicate
    0.37
    POSITIVE LOGITS
    wikipedia
    0.48
     объяс
    0.46
    詳しく
    0.46
     wyja
    0.45
    explain
    0.45
    explique
    0.45
     explaining
    0.44
    marginLeft
    0.43
     इंस्टीट
    0.43
     explains
    0.43
    Act Density 0.001%

    No Known Activations