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

    Neuronpedia

    INDEX
    Explanations

    references to race, particularly focusing on the concept of "white" in various contexts

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

    white and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.55
    stasia
    -0.51
    裟
    -0.42
     հղումներ
    -0.42
     φύ
    -0.41
    ppas
    -0.41
     disambiguazione
    -0.41
    sitis
    -0.40
    orgio
    -0.40
    toJson
    -0.40
    POSITIVE LOGITS
     white
    1.16
    White
    1.16
     White
    1.13
    white
    1.13
     WHITE
    1.11
    WHITE
    1.09
     whites
    0.93
     putih
    0.88
     Putih
    0.87
     blancas
    0.83
    Act Density 0.023%

    No Known Activations