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

    Neuronpedia

    INDEX
    Explanations

    race

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gul
    -0.07
    .Mockito
    -0.07
     Hugo
    -0.06
     PPP
    -0.06
     Coconut
    -0.06
     ngOn
    -0.06
     Jur
    -0.06
     Emit
    -0.06
    Bon
    -0.06
    plusplus
    -0.06
    POSITIVE LOGITS
     Race
    0.14
     race
    0.14
     races
    0.12
    Race
    0.12
    race
    0.10
     rac
    0.10
     racing
    0.10
     Races
    0.10
     Racing
    0.10
    ce
    0.09
    Act Density 0.013%

    No Known Activations