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

    Neuronpedia

    INDEX
    Explanations

    achievements through efforts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     всі
    -0.07
    니다
    -0.06
     studies
    -0.06
    ворення
    -0.06
     использ
    -0.06
    637
    -0.06
     тел
    -0.06
    Today
    -0.06
    !*\↵
    -0.06
     Train
    -0.06
    POSITIVE LOGITS
    太
    0.07
     minded
    0.07
    less
    0.07
     getProperty
    0.07
     York
    0.07
    yonel
    0.07
    月
    0.06
     etkili
    0.06
    obi
    0.06
     professionals
    0.06
    Act Density 0.091%

    No Known Activations