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

    Neuronpedia

    INDEX
    Explanations

    race and racism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gender
    0.59
     unfair
    0.54
     gender
    0.52
    Gender
    0.52
     Bias
    0.51
     inclus
    0.49
     biasing
    0.48
     bias
    0.47
     injust
    0.47
     Inclusive
    0.45
    POSITIVE LOGITS
     racial
    1.64
     interracial
    1.45
     racially
    1.43
    racial
    1.41
     racist
    1.39
     Racial
    1.36
     racism
    1.27
     rac
    1.12
     Racism
    1.09
     white
    1.05
    Act Density 0.033%

    No Known Activations