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

    Neuronpedia

    INDEX
    Explanations

    short answer summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ュー
    0.44
     এদিকে
    0.39
     tentunya
    0.37
    取り寄せ
    0.37
    IdentityProvider
    0.37
     Natürlich
    0.37
     conosc
    0.36
     방법에
    0.36
     évidemment
    0.36
     troughs
    0.36
    POSITIVE LOGITS
     summary
    1.65
     summarized
    1.52
     summarised
    1.48
    summary
    1.44
     Summary
    1.43
     summarize
    1.41
    Summary
    1.38
    总结
    1.38
     summarise
    1.35
     summarizes
    1.30
    Act Density 0.029%

    No Known Activations