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

    Neuronpedia

    INDEX
    Explanations

    references to racial themes and socio-political dynamics involving whiteness and racism

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

    views and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.51
    erçe
    -0.45
    ьаж
    -0.44
     stället
    -0.42
    endroit
    -0.40
     razão
    -0.39
    hésite
    -0.38
     Könige
    -0.37
     فريبيس
    -0.35
    arrêter
    -0.34
    POSITIVE LOGITS
     HFILL
    0.62
     OMITBAD
    0.60
    ReusableCell
    0.49
     onBind
    0.47
    protoimpl
    0.45
    namentales
    0.44
     tamb
    0.43
    antuan
    0.43
     Presidential
    0.42
    들의
    0.42
    Act Density 0.443%

    No Known Activations