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

    Neuronpedia

    INDEX
    Explanations

    references to nationalities or ethnic identities

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

    nationality and gender descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.43
    Glej
    -0.38
     depiction
    -0.35
     Frankel
    -0.35
     aksi
    -0.35
     flourished
    -0.34
    См
    -0.34
     disparu
    -0.34
     aldı
    -0.34
    问题的
    -0.33
    POSITIVE LOGITS
     يتيمه
    0.66
     female
    0.59
    casian
    0.58
    ########.
    0.57
    abancı
    0.55
     femininas
    0.54
     <=",
    0.54
    MethodManager
    0.53
    tvguidetime
    0.52
     EconPapers
    0.52
    Act Density 0.101%

    No Known Activations