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
    -changing
    -0.07
    800
    -0.07
    gos
    -0.07
     ripped
    -0.07
     Foam
    -0.07
     Change
    -0.07
     소
    -0.06
     چهار
    -0.06
    _STORE
    -0.06
     Thái
    -0.06
    POSITIVE LOGITS
     race
    0.08
     raced
    0.08
    _bl
    0.07
     races
    0.06
     Comparison
    0.06
     TEAM
    0.06
    竞
    0.06
     hel
    0.06
     anticipation
    0.06
     tallest
    0.06
    Act Density 0.007%

    No Known Activations