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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "en" and variations related to English language labels or references

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

    documentation links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.74
    ItemBackground
    -0.70
    RenderAtEndOf
    -0.67
    IVEREF
    -0.67
    Tikang
    -0.66
     desmotivaciones
    -0.65
    الحياه
    -0.65
    MessageOf
    -0.65
     ainfi
    -0.64
     AssemblyCulture
    -0.64
    POSITIVE LOGITS
     ob
    0.40
     
    0.40
    #!/
    0.39
    /
    0.39
    gulier
    0.39
     English
    0.38
    　
    0.37
     Salazar
    0.37
     web
    0.37
     for
    0.36
    Act Density 0.007%

    No Known Activations