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

    Neuronpedia

    INDEX
    Explanations

    references to traditional concepts and practices, particularly in relation to medicine and gender roles

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

    following "traditional"

    np_acts-logits-general · gemini-2.0-flash

    traditional or conventional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spéciales
    -0.64
     AssemblyTitle
    -0.63
    AddTagHelper
    -0.63
     particulières
    -0.58
     específico
    -0.57
     potenciales
    -0.57
     специально
    -0.57
     officielles
    -0.57
     specifico
    -0.57
     spéciaux
    -0.57
    POSITIVE LOGITS
    ists
    1.12
    ist
    0.91
     wisdom
    0.81
    izing
    0.81
    적인
    0.78
    ism
    0.78
     methods
    0.76
    적으로
    0.73
    izes
    0.72
    ized
    0.71
    Act Density 0.136%

    No Known Activations