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

    Neuronpedia

    INDEX
    Explanations

    discussions about systemic injustice and bias in society

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

    social justice/injustice

    np_acts-logits-general · gemini-2.0-flash

    marginalized communities and identities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     muß
    -0.95
     läßt
    -0.87
     idéia
    -0.82
     skall
    -0.78
     daß
    -0.71
     mußte
    -0.71
     HDTV
    -0.65
     müßte
    -0.63
     hubby
    -0.62
     retarded
    -0.61
    POSITIVE LOGITS
     LGBTQ
    0.96
     queer
    0.96
     spaces
    0.83
    yship
    0.79
     Queer
    0.79
    nullptr
    0.77
     ⁠
    0.76
    LGBT
    0.76
     onboarding
    0.75
     narratives
    0.75
    Act Density 0.390%

    No Known Activations