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

    Neuronpedia

    INDEX
    Explanations

    racial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    廠
    -0.07
     setTitle
    -0.06
    Hol
    -0.06
    주
    -0.06
    ัญช
    -0.06
     Κά
    -0.06
           ↵
    -0.06
    เจร
    -0.06
     Mastery
    -0.06
    ettle
    -0.06
    POSITIVE LOGITS
     Electrical
    0.07
     Telegraph
    0.07
     Eagle
    0.06
     Processor
    0.06
    thinkable
    0.06
    _BB
    0.06
     experiment
    0.06
    contres
    0.06
    viol
    0.06
     unravel
    0.06
    Act Density 0.000%

    No Known Activations