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

    Neuronpedia

    INDEX
    Explanations

    references to marginalized identities and their experiences

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

    marginalized communities and identities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toller
    -0.47
     pom
    -0.47
    ]');
    -0.42
    Toler
    -0.41
     Toler
    -0.39
    Tug
    -0.39
     wikipagina
    -0.39
    勾
    -0.39
    CodeAttribute
    -0.38
     ivelany
    -0.38
    POSITIVE LOGITS
     queer
    0.65
    queer
    0.55
     cuerpos
    0.52
     blackness
    0.51
     Black
    0.50
     centering
    0.50
     intersection
    0.49
     Queer
    0.48
     intersections
    0.47
     InputDecoration
    0.47
    Act Density 0.079%

    No Known Activations