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

    Neuronpedia

    INDEX
    Explanations

    references to external sources or links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    external links and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.37
    始
    -0.31
     Beiträge
    -0.31
    contrib
    -0.30
    nsch
    -0.30
    aka
    -0.30
     "---
    -0.30
     feel
    -0.28
    yin
    -0.28
    ませんか
    -0.28
    POSITIVE LOGITS
    Personensuche
    0.95
    Personendaten
    0.75
     lenker
    0.75
     ujednoznacz
    0.71
     виправивши
    0.68
    Datuak
    0.65
    msgTypes
    0.62
    WriteBarrier
    0.61
    الدراسه
    0.59
     ویکی‌پدی
    0.58
    Act Density 0.067%

    No Known Activations