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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence and smartness

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

    intelligence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lordships
    -0.47
    +#+#
    -0.47
    UrlResolution
    -0.46
     suyo
    -0.45
    tisseur
    -0.44
     sectoral
    -0.44
    MLLoader
    -0.43
    setCellStyle
    -0.43
    hésite
    -0.43
     getCustomer
    -0.43
    POSITIVE LOGITS
     intelligence
    0.88
     intelligen
    0.84
    Intelligence
    0.84
     Intelligen
    0.81
     intelligent
    0.81
     inteligencia
    0.80
     Intelligence
    0.79
     intellect
    0.77
    intelligence
    0.75
     intelig
    0.74
    Act Density 0.016%

    No Known Activations