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

    Neuronpedia

    INDEX
    Explanations

    references to organized groups, publications, and cultural initiatives

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

    named entities and their attributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.56
     للمعارف
    -0.56
    afficheront
    -0.44
    parsedMessage
    -0.43
    PropertyChanging
    -0.41
     Administrativna
    -0.39
    subpackage
    -0.38
    นะนำ
    -0.38
     menik
    -0.37
     ivelany
    -0.37
    POSITIVE LOGITS
     ModelExpression
    0.59
     parseFrom
    0.48
    onOptions
    0.47
     يتيمه
    0.46
    hubanes
    0.45
     dealt
    0.45
     AppModule
    0.44
    \{\\
    0.43
    setVerticalGroup
    0.43
    aarrggbb
    0.42
    Act Density 0.055%

    No Known Activations