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

    Neuronpedia

    INDEX
    Explanations

    keywords related to affirmative action and racial equality issues

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

    affirmative action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kandang
    -0.48
     sekali
    -0.44
    grunns
    -0.43
    ✨:
    -0.43
    sbereich
    -0.43
    caval
    -0.42
    unnel
    -0.41
     tempio
    -0.41
    ungszeit
    -0.40
     regulars
    -0.40
    POSITIVE LOGITS
     damska
    0.42
    RTEE
    0.38
    arakat
    0.38
    posedge
    0.38
     resourceCulture
    0.38
    rungsseite
    0.37
    ActionCreators
    0.37
     StatelessWidget
    0.36
    ❹
    0.36
    ParallelGroup
    0.35
    Act Density 0.097%

    No Known Activations