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

    Neuronpedia

    INDEX
    Explanations

    references to categories and examples within a structured format

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

    example or references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.52
    //</
    -0.47
    XmlElement
    -0.47
    pyx
    -0.47
    -0.46
    cookieParser
    -0.46
     NavController
    -0.46
     endforeach
    -0.45
     الرياضيه
    -0.45
     JpaRepository
    -0.45
    POSITIVE LOGITS
    KommentareTeilen
    0.42
    ьаж
    0.39
    новништво
    0.36
    ModelAdmin
    0.35
    cloudflare
    0.35
    fjspx
    0.35
     Vers
    0.35
    SequentialGroup
    0.35
     lượt
    0.35
     surla
    0.34
    Act Density 0.188%

    No Known Activations