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

    Neuronpedia

    INDEX
    Explanations

    technical solutions, consent, warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Conclusion
    0.36
    warp
    0.35
     полного
    0.35
    öst
    0.35
     Led
    0.35
     sentiments
    0.35
     critic
    0.34
    adet
    0.34
    Coast
    0.34
    දය
    0.34
    POSITIVE LOGITS
    最新的
    0.41
    峇
    0.40
    実際に
    0.39
     eligibility
    0.38
     त
    0.38
     singleRun
    0.38
     jual
    0.37
    歷
    0.37
    最新
    0.37
     sưu
    0.37
    Act Density 0.000%

    No Known Activations