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

    Neuronpedia

    INDEX
    Explanations

    From

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhựa
    -0.07
     الشعر
    -0.07
     nuis
    -0.07
     oral
    -0.07
     utrecht
    -0.06
    тен
    -0.06
     maté
    -0.06
    խ
    -0.06
     fem
    -0.06
    辀
    -0.06
    POSITIVE LOGITS
    Studio
    0.08
    滨州
    0.07
     volunteer
    0.07
     paycheck
    0.07
    结束了
    0.07
     WARN
    0.07
    -profile
    0.07
     Screening
    0.06
    주
    0.06
     shelters
    0.06
    Act Density 0.001%

    No Known Activations