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
     PPP
    -0.07
    gtk
    -0.07
    etheless
    -0.07
     consortium
    -0.06
    öm
    -0.06
    apeut
    -0.06
    ToOne
    -0.06
    todo
    -0.06
    ügen
    -0.06
     intim
    -0.06
    POSITIVE LOGITS
     Race
    0.19
     race
    0.19
    Race
    0.17
     races
    0.16
     Races
    0.14
    race
    0.12
     rac
    0.11
     racing
    0.11
     raced
    0.10
     Rac
    0.10
    Act Density 0.013%

    No Known Activations