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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize individuality and personal expression

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

    unique stylish qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gameserver
    -0.36
     réc
    -0.35
    }`)
    -0.34
     agré
    -0.33
    """)
    -0.32
     applicant
    -0.32
    Initializer
    -0.32
    })*/
    -0.32
     Eureka
    -0.32
     encouraging
    -0.31
    POSITIVE LOGITS
     BoxFit
    0.64
     FetchType
    0.54
    parsedMessage
    0.50
     tartalomajánló
    0.50
     fashionable
    0.48
    fashionable
    0.48
    ViewImports
    0.47
    Vidite
    0.47
     subtly
    0.47
    subtle
    0.47
    Act Density 0.023%

    No Known Activations