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

    Neuronpedia

    INDEX
    Explanations

    discussions about personal transformation and purpose

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

    learned, discovered, created

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.65
    Hentet
    -0.63
    yntaxException
    -0.61
     péché
    -0.58
    المناصب
    -0.56
    IntoConstraints
    -0.56
    delaire
    -0.55
    Autoritní
    -0.54
     ExecuteAsync
    -0.52
    GEBURTSDATUM
    -0.51
    POSITIVE LOGITS
     research
    0.39
     пришлось
    0.38
     learned
    0.37
     investigación
    0.36
     repaired
    0.35
     re
    0.35
     researched
    0.35
    rag
    0.34
     researching
    0.34
     healed
    0.33
    Act Density 0.017%

    No Known Activations