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

    Neuronpedia

    INDEX
    Explanations

    instances of people expressing their opinions or writing about a topic

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

    indicates user contribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.61
    pexpr
    -0.54
     []).
    -0.54
    UrlResolution
    -0.54
     disambiguazione
    -0.54
     leſs
    -0.53
    IntoConstraints
    -0.52
    şört
    -0.50
    )».
    -0.50
     Wicidata
    -0.50
    POSITIVE LOGITS
     suje
    0.38
     author
    0.38
     mwenye
    0.37
     @
    0.36
    Referanser
    0.35
     posted
    0.35
     profess
    0.35
    archives
    0.35
     username
    0.34
     guilty
    0.34
    Act Density 0.135%

    No Known Activations