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

    Neuronpedia

    INDEX
    Explanations

    research-related terminology and references

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

    academic research and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.70
    AndEndTag
    -0.66
    SharedCtor
    -0.64
     disambiguazione
    -0.63
    #+#
    -0.62
     
    -0.59
    fjspx
    -0.56
    IndentedString
    -0.56
     Италијани
    -0.56
     <>",
    -0.55
    POSITIVE LOGITS
    期刊论文
    0.59
     Forschung
    0.57
     ricerche
    0.55
     researchers
    0.54
     chercheurs
    0.54
     연구
    0.54
     thèse
    0.52
     proef
    0.51
     tutkim
    0.51
    Researchers
    0.51
    Act Density 0.275%

    No Known Activations